© 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. 93840
    Prev
    Next
    INDEX
    Explanations

    rain

    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
    liner
    -0.63
    wind
    -0.59
    lined
    -0.57
     ingenieros
    -0.54
    ono
    -0.53
    tf
    -0.53
    ThroughAttribute
    -0.52
    WIND
    -0.52
    mah
    -0.50
    LIN
    -0.50
    POSITIVE LOGITS
    ized
    0.75
    \{\\
    0.65
    ization
    0.62
    ous
    0.60
     Ciro
    0.60
    selves
    0.56
    hood
    0.55
    al
    0.55
     Koto
    0.53
    ative
    0.53
    Activations Density 0.147%

    No Known Activations