© 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. 5214
    Prev
    Next
    INDEX
    Explanations

    of

    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
     étoit
    -0.72
    aarrggbb
    -0.71
    PreferredItem
    -0.65
    \{\\
    -0.62
     blijft
    -0.62
     avulla
    -0.62
    HomeAsUpEnabled
    -0.62
     trasparente
    -0.61
    principalColumn
    -0.61
     bleef
    -0.58
    POSITIVE LOGITS
     entitlements
    0.47
    taminophen
    0.45
     modern
    0.45
     linkovi
    0.44
     "'"
    0.41
     جغرافيا
    0.40
    Portail
    0.39
    liction
    0.39
    ResponseModel
    0.39
     corporate
    0.38
    Activations Density 0.001%

    No Known Activations