© 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. 0-CLT-HP
    7. 1205
    Prev
    Next
    INDEX
    Explanations

    s

    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
     
    -0.72
    i
    -0.69
    s
    -0.68
     to
    -0.67
    t
    -0.66
    ↵
    -0.62
    a
    -0.61
    o
    -0.61
     (
    -0.60
    e
    -0.59
    POSITIVE LOGITS
    ^(@)
    1.24
     doubtnut
    1.19
    setVerticalGroup
    1.16
    évaluateur
    1.16
     Efq
    1.12
     resourceCulture
    1.04
    ՚
    1.04
     ―――――
    1.03
     ་་
    1.02
    \<^
    1.01
    Activations Density 0.032%

    No Known Activations