© 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. 39820
    Prev
    Next
    INDEX
    Explanations

    amplitude

    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
     expression
    -0.84
     Expression
    -0.83
     Expressions
    -0.82
    KommentareTeilen
    -0.81
    CodeAttribute
    -0.80
     expressive
    -0.80
     expressions
    -0.79
    Expressions
    -0.78
     Majefty
    -0.77
     StringTokenizer
    -0.76
    POSITIVE LOGITS
     venons
    0.52
     تضيفلها
    0.48
     mães
    0.43
     mère
    0.43
    gående
    0.42
    us
    0.42
     gavetas
    0.42
     kautta
    0.41
    ерез
    0.41
     års
    0.40
    Activations Density 0.033%

    No Known Activations