© 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. 1-CLT-HP
    7. 45639
    Prev
    Next
    INDEX
    Explanations

    investigate

    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
     незавершена
    -0.79
    AndEndTag
    -0.76
     investigate
    -0.67
     للمعارف
    -0.66
     виправивши
    -0.65
     Numerade
    -0.65
     ProtoMessage
    -0.65
     investigated
    -0.64
     تانيه
    -0.63
    ГЛА
    -0.63
    POSITIVE LOGITS
     on
    0.82
     into
    0.80
     how
    0.78
     about
    0.76
     whether
    0.64
     the
    0.62
    into
    0.59
     tentang
    0.57
     asupra
    0.56
     روی
    0.54
    Activations Density 0.036%

    No Known Activations