© 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. 14797
    Prev
    Next
    INDEX
    Explanations

    versial

    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
    ">',
    -0.60
    upol
    -0.57
    IBOutlet
    -0.57
    Бахар
    -0.56
    versial
    -0.55
    httphttps
    -0.52
    expandindo
    -0.50
    AddRange
    -0.50
    :+:
    -0.50
     tramonto
    -0.50
    POSITIVE LOGITS
    Попис
    0.53
    setPointSize
    0.52
     mis
    0.50
    mso
    0.47
    mishes
    0.46
     ويكي
    0.46
    batis
    0.45
    tahui
    0.45
    mis
    0.45
    tho
    0.45
    Activations Density 0.036%

    No Known Activations