© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6403
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Czech Republic

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1937
    +0.16
    0.5%
    298
    +0.13
    0.5%
    131
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.16
    0.03
    899
    +0.13
    0.02
    131
    +0.12
    0.01
    Negative Logits
     Wiking
    -0.94
     Krzysz
    -0.88
     Szw
    -0.84
     Dichter
    -0.78
     lapto
    -0.78
     kawa
    -0.77
     jubile
    -0.76
     Zwiebel
    -0.75
     Francus
    -0.75
     Spani
    -0.73
    POSITIVE LOGITS
     Daven
    1.42
     Confu
    1.32
     McLaugh
    1.32
     Mlle
    1.30
     Shakspeare
    1.26
     Whence
    1.22
     unwarran
    1.22
     Eccle
    1.21
     Righ
    1.20
     Cze
    1.20
    Activations Density 0.109%

    No Known Activations