© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38671
    Prev
    Next
    INDEX
    Explanations

    neapolis

    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
    APOLIS
    -3.11
     viewDid
    -0.67
    NUMX
    -0.66
    PullParser
    -0.65
    SourceChecksum
    -0.65
    ClientSize
    -0.63
    发表于
    -0.62
    apolis
    -0.62
    OLIS
    -0.59
    inguez
    -0.59
    POSITIVE LOGITS
    المناصب
    0.56
     Hered
    0.55
     الرياضيه
    0.52
    Autoritní
    0.52
     Réalisation
    0.52
     chini
    0.49
    styleType
    0.46
     Throat
    0.46
     lyd
    0.44
     chamber
    0.44
    Activations Density 1.587%

    No Known Activations