© 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. 5-CLT-HP
    7. 91466
    Prev
    Next
    INDEX
    Explanations

    academic/legal documents

    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
    principalColumn
    -0.91
     Efq
    -0.86
    aarrggbb
    -0.84
     myſelf
    -0.83
     avoient
    -0.81
     pleaſure
    -0.79
     purpoſe
    -0.79
    bootstrapcdn
    -0.78
     preſent
    -0.76
    Condol
    -0.75
    POSITIVE LOGITS
    e
    0.71
    er
    0.70
    o
    0.63
    i
    0.61
    ing
    0.61
    y
    0.58
    n
    0.57
    s
    0.57
    a
    0.55
    k
    0.55
    Activations Density 0.018%

    No Known Activations