© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38976
    Prev
    Next
    INDEX
    Explanations

    stealing

    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
    s
    -0.73
    ly
    -0.56
     Small
    -0.49
    sav
    -0.48
     Food
    -0.44
    lior
    -0.43
     crystallized
    -0.43
    ilmente
    -0.43
    ;->
    -0.42
     Eating
    -0.42
    POSITIVE LOGITS
    клопе
    0.77
    +#+
    0.71
     protoimpl
    0.70
    RenderAtEndOf
    0.68
     résine
    0.61
    derry
    0.61
    下载附件
    0.59
    CodedInputStream
    0.59
     مشين
    0.59
    copg
    0.59
    Activations Density 0.104%

    No Known Activations