© 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. 90969
    Prev
    Next
    INDEX
    Explanations

    code and errors

    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
     Chalk
    -0.85
    Chalk
    -0.76
     Lock
    -0.75
     onCreateView
    -0.66
    StoryboardSegue
    -0.65
    Xna
    -0.63
    onViewCreated
    -0.63
    taxia
    -0.62
    setupUi
    -0.60
     Engines
    -0.59
    POSITIVE LOGITS
    ed
    0.62
    ies
    0.54
    mor
    0.51
    lands
    0.50
    hips
    0.49
    ments
    0.49
    UMEN
    0.48
    ors
    0.48
    amore
    0.47
    umen
    0.47
    Activations Density 1.668%

    No Known Activations