© 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. 5-CLT-HP
    7. 2063
    Prev
    Next
    INDEX
    Explanations

    intensity

    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
    MigrationBuilder
    -0.71
     particuliers
    -0.69
    oredCriteria
    -0.67
    EditorBrowsable
    -0.66
     purpoſe
    -0.65
     pleaſure
    -0.63
     nahilalakip
    -0.63
    ']],
    -0.63
     houſe
    -0.63
     enfans
    -0.61
    POSITIVE LOGITS
    Argb
    0.54
    ftagPool
    0.50
     rate
    0.50
    createCell
    0.49
     only
    0.47
     something
    0.47
     start
    0.47
     risk
    0.46
     politics
    0.45
     hugely
    0.45
    Activations Density 0.008%

    No Known Activations