© 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. 0-CLT-HP
    7. 1166
    Prev
    Next
    INDEX
    Explanations

    World War II

    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
    yntaxException
    -0.64
    InSection
    -0.61
     مرئيه
    -0.59
     Ouvrez
    -0.58
    WithIOException
    -0.58
    픈
    -0.52
     eléctricos
    -0.52
     lèvres
    -0.51
    UnsafeEnabled
    -0.50
     gemeenten
    -0.50
    POSITIVE LOGITS
     cherchés
    0.59
    =$?
    0.58
     itſelf
    0.57
     reaſon
    0.56
     Efq
    0.56
    IFORN
    0.56
     AppCompatTheme
    0.55
    <bos>
    0.54
    hicle
    0.54
    enderror
    0.53
    Activations Density 0.213%

    No Known Activations