© 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. 2208
    Prev
    Next
    INDEX
    Explanations

    archived or recorded

    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
    Vidite
    -0.66
     MainAxisSize
    -0.63
    moiselle
    -0.62
     AssemblyVersion
    -0.57
    })->
    -0.57
    DoubleQuotes
    -0.56
    NullCheck
    -0.55
    (!__
    -0.54
    Nationalité
    -0.54
    ActivityCompat
    -0.54
    POSITIVE LOGITS
     news
    0.64
     News
    0.64
     webinar
    0.58
     nieuws
    0.57
    news
    0.54
     webinars
    0.52
    News
    0.52
     anciens
    0.51
     NEWS
    0.50
    forum
    0.49
    Activations Density 0.003%

    No Known Activations