© 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. 0-CLT-HP
    7. 42475
    Prev
    Next
    INDEX
    Explanations

    origins, locations

    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
     Mix
    -0.87
    Mix
    -0.79
    mix
    -0.71
    MIX
    -0.69
     gloire
    -0.67
     avoient
    -0.66
    ndose
    -0.66
    patrón
    -0.66
     MIX
    -0.65
     déput
    -0.65
    POSITIVE LOGITS
    e
    0.96
    s
    0.91
    es
    0.91
    en
    0.76
    ers
    0.73
    y
    0.69
    er
    0.68
    a
    0.62
    se
    0.62
    ed
    0.60
    Activations Density 0.056%

    No Known Activations