© 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. 4576
    Prev
    Next
    INDEX
    Explanations

    if/whether

    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
    PreferredItem
    -0.70
     Мексичка
    -0.69
    TintMode
    -0.68
    Abitanti
    -0.67
    Personensuche
    -0.67
    izoen
    -0.65
    ViewFeatures
    -0.65
     Италијани
    -0.64
     Itself
    -0.64
     يتيمه
    -0.60
    POSITIVE LOGITS
     the
    0.81
     there
    0.77
    findpost
    0.68
     your
    0.54
     onFailure
    0.47
     you
    0.46
    ApiProperty
    0.44
     danni
    0.44
    yorsunuz
    0.43
     someone
    0.42
    Activations Density 0.003%

    No Known Activations