© 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. 92697
    Prev
    Next
    INDEX
    Explanations

    archives

    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
    addSubview
    -0.46
     потер
    -0.43
    קט
    -0.41
     perdere
    -0.41
    dius
    -0.41
     addSubview
    -0.41
     Lieberman
    -0.41
    лок
    -0.41
    ngua
    -0.41
    ##
    -0.40
    POSITIVE LOGITS
     Superhosts
    0.78
     تضيفلها
    0.76
    MLLoader
    0.74
     Roskov
    0.72
    LookAnd
    0.71
     ModelExpression
    0.69
     TextInputType
    0.68
     للاسماء
    0.68
    InputBorder
    0.67
    astéro
    0.66
    Activations Density 0.006%

    No Known Activations