© 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. 1-CLT-HP
    7. 9893
    Prev
    Next
    INDEX
    Explanations

    been

    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
     للمعارف
    -0.73
    VersionUID
    -0.66
     BoxFit
    -0.65
    NameInMap
    -0.65
     arşivlendi
    -0.65
    ArgsConstructor
    -0.62
    AxisAlignment
    -0.62
    RTLD
    -0.61
    RuleContext
    -0.60
    StandardCharsets
    -0.59
    POSITIVE LOGITS
     demikian
    0.48
    umą
    0.48
    (',');
    0.48
    jména
    0.46
    それでも
    0.46
    ?";
    0.45
    bör
    0.44
    やや
    0.44
     ';
    0.44
     devriez
    0.43
    Activations Density 0.035%

    No Known Activations