© 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. 91006
    Prev
    Next
    INDEX
    Explanations

    neural

    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
    NUMX
    -0.98
    )");
    -0.93
    )";
    -0.86
     Neural
    -0.82
    expandindo
    -0.81
    :][
    -0.80
     noDo
    -0.80
    AutoScaleMode
    -0.79
    ".
    -0.79
     négociations
    -0.78
    POSITIVE LOGITS
    s
    0.97
    ی
    0.60
    sna
    0.51
    ↵
    0.46
    y
    0.46
    san
    0.44
    sana
    0.44
    she
    0.43
    sho
    0.43
    sand
    0.43
    Activations Density 0.502%

    No Known Activations