© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3640
    Prev
    Next
    INDEX
    Explanations

    references to the term "Per" as part of various phrases or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    528
    +0.17
    1.0%
    1059
    +0.15
    0.9%
    50
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1059
    +0.17
    0.04
    281
    +0.15
    0.03
    528
    +0.15
    0.03
    Negative Logits
    <bos>
    -2.14
    archiviato
    -0.66
     zobaczyć
    -0.59
     accommodate
    -0.57
    enaam
    -0.56
    displayquote
    -0.55
     avoid
    -0.54
     eliminate
    -0.54
    glBindTexture
    -0.53
    씻
    -0.53
    POSITIVE LOGITS
     Per
    1.28
     PER
    1.23
     Persi
    1.20
    Per
    1.18
     Peri
    1.10
     Perfor
    1.08
     perpé
    1.08
     Perla
    1.05
     Perks
    1.05
     Ename
    1.05
    Activations Density 0.082%

    No Known Activations