© 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. 15432
    Prev
    Next
    INDEX
    Explanations

    origin/identity/disease

    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
    IsMutable
    -0.75
     minority
    -0.74
     minorities
    -0.67
    @[+][
    -0.66
    exitRule
    -0.65
    قایناق‌لار
    -0.63
     Minority
    -0.62
    tonsoft
    -0.61
    DockStyle
    -0.57
     يتيمه
    -0.57
    POSITIVE LOGITS
    es
    0.56
    ing
    0.53
    ed
    0.53
    laş
    0.49
     reliance
    0.48
    XtraBars
    0.48
    Xna
    0.47
    ial
    0.46
    ese
    0.46
    mentaires
    0.45
    Activations Density 0.023%

    No Known Activations