© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93093
    Prev
    Next
    INDEX
    Explanations

    enumer

    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
     Anſ
    -0.85
     Majefty
    -0.77
     Articles
    -0.77
     itſelf
    -0.75
    Vidite
    -0.75
     Theſe
    -0.74
     myſelf
    -0.74
     beginnetje
    -0.73
    ItemBackground
    -0.73
    outchouc
    -0.72
    POSITIVE LOGITS
    i
    0.94
    e
    0.76
    o
    0.74
    a
    0.73
    y
    0.73
    el
    0.52
    en
    0.50
    s
    0.50
    al
    0.50
    ي
    0.50
    Activations Density 0.061%

    No Known Activations