© 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. 4-CLT-HP
    7. 4337
    Prev
    Next
    INDEX
    Explanations

    )

    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
     Pollock
    -0.46
    anh
    -0.45
    äng
    -0.45
     ла
    -0.44
     super
    -0.44
    auto
    -0.44
    stad
    -0.43
    сти
    -0.43
     auto
    -0.43
    СТИ
    -0.43
    POSITIVE LOGITS
    Personendaten
    0.84
     disambiguazione
    0.83
    saraba
    0.77
    WebVitals
    0.68
    WireFormatLite
    0.68
    rawDesc
    0.66
     }{@
    0.66
     utafitiHapana
    0.65
     дописавши
    0.65
    aarrggbb
    0.65
    Activations Density 0.003%

    No Known Activations