© 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. 5-CLT-HP
    7. 98244
    Prev
    Next
    INDEX
    Explanations

    crime

    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
     sexual
    -0.50
     gian
    -0.47
    ’
    -0.46
     dead
    -0.46
    UserScript
    -0.45
     giochi
    -0.44
     sexually
    -0.42
     Aris
    -0.41
    <bos>
    -0.41
     sex
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    0.79
    __*/
    0.78
     ModelExpression
    0.72
    ---|---|
    0.70
    iastes
    0.69
     للاسماء
    0.68
    BeginContext
    0.66
    ReusableCell
    0.66
    cellaneous
    0.63
    igshid
    0.63
    Activations Density 0.005%

    No Known Activations