© 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. 38999
    Prev
    Next
    INDEX
    Explanations

    some

    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
     Some
    -1.19
     varandra
    -0.98
    Some
    -0.95
     dieux
    -0.94
     cérami
    -0.93
     vérit
    -0.92
     leçons
    -0.91
     prochaines
    -0.91
     pouvoirs
    -0.90
     larmes
    -0.89
    POSITIVE LOGITS
    day
    1.04
     of
    0.95
    days
    0.80
    time
    0.73
    more
    0.73
    t
    0.72
    d
    0.66
    mi
    0.65
     are
    0.64
    place
    0.64
    Activations Density 0.801%

    No Known Activations