© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 9760
    Prev
    Next
    INDEX
    Explanations

    ism

    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
    ism
    -1.12
    isms
    -0.90
    ISM
    -0.86
    isme
    -0.83
    ismen
    -0.81
    ismus
    -0.75
    ismo
    -0.73
    ismes
    -0.67
    idopsis
    -0.66
    ISMO
    -0.66
    POSITIVE LOGITS
    "):
    
    0.59
    \"");
    0.58
    ."],
    0.54
    ')")
    0.52
    //{
    
    0.52
    />";
    0.51
    ."]
    0.48
    __":
    
    0.47
    PhysRev
    0.47
    %");
    0.47
    Activations Density 0.439%

    No Known Activations