© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1156
    Prev
    Next
    INDEX
    Explanations

    spelling

    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
     spelling
    -2.36
     spelled
    -2.11
     spell
    -2.03
    spelling
    -1.81
     spelt
    -1.79
    spell
    -1.70
     spellings
    -1.64
     Spell
    -1.63
    Spell
    -1.52
    Spelling
    -1.48
    POSITIVE LOGITS
     out
    0.68
     (
    0.56
    sub
    0.54
    kan
    0.52
    mark
    0.50
    star
    0.50
    __*/
    0.50
    ser
    0.50
    fi
    0.49
     године
    0.49
    Activations Density 0.127%

    No Known Activations