© 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. 4-CLT-HP
    7. 197
    Prev
    Next
    INDEX
    Explanations

    have

    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
    GEBURTSDATUM
    -0.95
     تضيفلها
    -0.79
    ьаж
    -0.69
    AutoresizingMask
    -0.69
     AssemblyCulture
    -0.68
     onData
    -0.68
    HasAnnotation
    -0.65
    المكان
    -0.65
     становника
    -0.64
    ftagPool
    -0.63
    POSITIVE LOGITS
     مرئيه
    0.49
     always
    0.48
     so
    0.46
     long
    0.45
     even
    0.43
     previously
    0.43
    comod
    0.42
     يتيمه
    0.40
     bet
    0.39
     speculation
    0.39
    Activations Density 0.004%

    No Known Activations