© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90953
    Prev
    Next
    INDEX
    Explanations

    learns

    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
     Ending
    -0.83
     Anſ
    -0.71
     communicates
    -0.69
     Efq
    -0.68
     ainfi
    -0.68
     learns
    -0.67
     clô
    -0.65
     Houſe
    -0.65
    Ending
    -0.63
    ending
    -0.62
    POSITIVE LOGITS
     fine
    0.76
     the
    0.68
     and
    0.66
     poor
    0.61
     he
    0.60
     well
    0.60
     M
    0.59
     long
    0.59
     Fine
    0.58
     My
    0.58
    Activations Density 0.354%

    No Known Activations