© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94608
    Prev
    Next
    INDEX
    Explanations

    post

    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
    ReusableCell
    -0.77
     يتيمه
    -0.69
    =$?
    -0.68
    principalColumn
    -0.63
    astify
    -0.61
    posedge
    -0.60
     permanentes
    -0.57
     shutil
    -0.57
     للمعارف
    -0.57
     ContentValues
    -0.56
    POSITIVE LOGITS
    <bos>
    0.79
     some
    0.66
     something
    0.58
     that
    0.57
     the
    0.57
     their
    0.57
     a
    0.56
     things
    0.54
     any
    0.52
    webElement
    0.50
    Activations Density 0.036%

    No Known Activations