© 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. 1140
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     myſelf
    -1.22
     itſelf
    -1.13
     pleaſure
    -1.09
     Efq
    -1.06
     leaſt
    -1.03
     Monfieur
    -1.02
     raiſ
    -1.01
     reaſon
    -1.00
     Jefus
    -0.99
     whoſe
    -0.99
    POSITIVE LOGITS
    ,
    1.12
    .
    1.10
    -
    1.01
    ;
    0.95
    :
    0.87
    (
    0.80
    /
    0.80
    )
    0.77
    "
    0.69
    ?
    0.68
    Activations Density 0.842%

    No Known Activations