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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 434
    Prev
    Next
    INDEX
    Explanations

    references to Adolf Hitler

    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
    1492
    +0.16
    0.8%
    1671
    +0.13
    0.7%
    1994
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.16
    0.01
    1097
    +0.13
    0.03
    227
    +0.12
    0.03
    Negative Logits
    <bos>
    -1.51
    لينكات
    -0.68
    Географи
    -0.66
    Cal
    -0.65
     Cal
    -0.63
    styleType
    -0.60
    setDo
    -0.60
    namespace
    -0.59
    cal
    -0.59
    hdysval
    -0.58
    POSITIVE LOGITS
     alberto
    1.50
     maneu
    1.45
     increa
    1.43
     emphat
    1.43
     affor
    1.41
     thut
    1.40
     impra
    1.40
     fortn
    1.39
     secon
    1.35
     volunte
    1.33
    Activations Density 0.164%

    No Known Activations