© 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. 15879
    Prev
    Next
    INDEX
    Explanations

    make

    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
    ValueStyle
    -0.74
    tagHelperRunner
    -0.68
     houſe
    -0.60
     perfons
    -0.59
     onCreateView
    -0.58
     onPostExecute
    -0.58
    InputBorder
    -0.58
    LookAnd
    -0.57
     CreateTagHelper
    -0.56
    localctx
    -0.55
    POSITIVE LOGITS
     sense
    0.58
    [](
    0.49
     sesama
    0.48
    AddWithValue
    0.48
     donnée
    0.48
     better
    0.46
    meral
    0.46
    arsk
    0.45
    ]--;
    0.45
     thing
    0.45
    Activations Density 0.009%

    No Known Activations