© 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. 20-CLT-HP
    7. 77758
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act-logits · 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
     CURIAM
    -0.77
     JpaRepository
    -0.68
    currentColor
    -0.60
     tué
    -0.59
    uertos
    -0.57
     pouvoit
    -0.57
    detectChanges
    -0.56
     Intelligent
    -0.56
    __;
    -0.55
    rašymas
    -0.55
    POSITIVE LOGITS
    رشف
    0.50
    rénées
    0.50
    rolid
    0.47
    ViewImports
    0.47
    entemente
    0.45
    ENR
    0.45
     EN
    0.44
     en
    0.44
    InjectAttribute
    0.43
    VolleyError
    0.43
    Activations Density 0.000%

    No Known Activations