© 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. 44139
    Prev
    Next
    INDEX
    Explanations

    Mexico

    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
    ^(@)
    -1.11
     auroit
    -1.00
     feroit
    -0.97
     avoient
    -0.96
    出版年
    -0.94
     Efq
    -0.93
    IBLIO
    -0.92
    Diweddarwch
    -0.92
     pouvoit
    -0.92
     auffi
    -0.91
    POSITIVE LOGITS
     
    0.72
     (
    0.67
    ,
    0.67
    .
    0.60
    as
    0.59
    2
    0.59
    File
    0.59
     and
    0.58
    ↵
    0.57
    on
    0.57
    Activations Density 0.180%

    No Known Activations