© 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. 92047
    Prev
    Next
    INDEX
    Explanations

    isotopes

    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
     isotopes
    -0.74
    DoubleQuotes
    -0.73
    quakes
    -0.70
    atellite
    -0.63
    WriteLiteral
    -0.57
    RectangleBorder
    -0.56
    ateral
    -0.56
     INVENTION
    -0.56
     MonoBehaviour
    -0.55
    Hauptartikel
    -0.54
    POSITIVE LOGITS
    saraba
    0.58
     Shakspeare
    0.58
     Britann
    0.52
     ſtate
    0.52
     getCity
    0.52
     Prova
    0.52
     Anſ
    0.51
     يتيمه
    0.51
    ποι
    0.50
    MergeFrom
    0.50
    Activations Density 0.128%

    No Known Activations