© 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. 4-CLT-HP
    7. 4444
    Prev
    Next
    INDEX
    Explanations

    adverbs

    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
    must
    -0.79
     avoient
    -0.77
    Must
    -0.77
    MUST
    -0.74
     auroit
    -0.73
     étoit
    -0.73
     muszą
    -0.71
     ſeveral
    -0.70
     Must
    -0.69
    évaluateur
    -0.69
    POSITIVE LOGITS
     resort
    0.52
     worry
    0.51
    ers
    0.50
     choose
    0.50
     guard
    0.50
     cross
    0.50
     be
    0.50
     consider
    0.48
    ResumeLayout
    0.47
    ERS
    0.47
    Activations Density 0.005%

    No Known Activations