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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1192
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    UserScript
    -0.90
     disambiguazione
    -0.84
     Autorizaciones
    -0.79
    StoryboardSegue
    -0.79
     Comprometido
    -0.78
    ThroughAttribute
    -0.76
     EconPapers
    -0.75
     فريبيس
    -0.75
     Italijanski
    -0.73
    حياته
    -0.73
    POSITIVE LOGITS
     to
    0.58
     by
    0.50
     for
    0.46
     at
    0.44
     in
    0.42
     on
    0.39
     väli
    0.38
     sendi
    0.37
     discuss
    0.37
     learning
    0.36
    Activations Density 0.005%

    No Known Activations