© 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. 38805
    Prev
    Next
    INDEX
    Explanations

    time

    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
    MLLoader
    -1.23
     itſelf
    -1.23
     reaſon
    -1.13
    ]--;
    -1.13
     Jefus
    -1.12
     themſelves
    -1.11
     himſelf
    -1.09
    ^(@)
    -1.09
     myſelf
    -1.09
     iſt
    -1.07
    POSITIVE LOGITS
    ,
    0.79
    .
    0.68
     and
    0.62
    l
    0.61
     for
    0.58
     to
    0.57
    y
    0.54
     (
    0.53
     as
    0.53
     et
    0.52
    Activations Density 0.032%

    No Known Activations