© 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. 4404
    Prev
    Next
    INDEX
    Explanations

    and

    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
    turning
    -0.63
    shall
    -0.59
    doing
    -0.57
     venait
    -0.57
     textStatus
    -0.57
    saying
    -0.56
    '])){
    -0.56
    didSet
    -0.56
    not
    -0.56
    /******/
    -0.56
    POSITIVE LOGITS
     be
    0.99
     settle
    0.66
     take
    0.66
     find
    0.66
     decide
    0.65
     think
    0.65
     apply
    0.63
     enjoy
    0.63
     try
    0.61
     make
    0.60
    Activations Density 0.008%

    No Known Activations