© 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. 0-CLT-HP
    7. 95413
    Prev
    Next
    INDEX
    Explanations

    ies

    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
     
    -0.50
     (
    -0.44
     pro
    -0.44
     …
    -0.43
    .
    -0.42
    <eos>
    -0.42
    da
    -0.40
     k
    -0.39
     by
    -0.39
     other
    -0.39
    POSITIVE LOGITS
     myſelf
    1.00
     Efq
    0.96
    ſelf
    0.96
     himſelf
    0.94
     Jefus
    0.94
     itſelf
    0.94
     themſelves
    0.94
    ^(@)
    0.93
    <bos>
    0.91
    ſelves
    0.91
    Activations Density 0.068%

    No Known Activations