© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15972
    Prev
    Next
    INDEX
    Explanations

    fee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fee
    -0.70
    rilis
    -0.69
    fees
    -0.61
    gether
    -0.59
    ModelSerializer
    -0.59
     fees
    -0.57
    ISODE
    -0.57
    fee
    -0.55
     Fee
    -0.53
    likle
    -0.53
    POSITIVE LOGITS
    Искәрмәләр
    0.64
    BeginContext
    0.62
     onPostExecute
    0.60
    AndEndTag
    0.56
    ChildScrollView
    0.51
     of
    0.51
    <bos>
    0.50
    mergeFrom
    0.49
    printStackTrace
    0.49
    帖最后由
    0.48
    Activations Density 0.043%

    No Known Activations