© 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. 5507
    Prev
    Next
    INDEX
    Explanations

    academic language

    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
    المراجع
    -0.51
     представляет
    -0.46
    مصادر
    -0.44
    assas
    -0.44
     يلي
    -0.42
    مراجع
    -0.42
    ývá
    -0.41
    adillas
    -0.40
     通販
    -0.40
     unha
    -0.40
    POSITIVE LOGITS
    RectangleBorder
    0.82
    Portail
    0.81
    WriteAttribute
    0.78
    LookAnd
    0.78
    Tikang
    0.77
    DrawerToggle
    0.73
    mybatisplus
    0.71
    Geplaatst
    0.71
     بيها
    0.70
    tagHelperRunner
    0.67
    Activations Density 0.014%

    No Known Activations