© 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. 45295
    Prev
    Next
    INDEX
    Explanations

    computers

    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
    -1.15
     faſt
    -1.06
     itſelf
    -0.97
     himſelf
    -0.95
     juſ
    -0.93
     becauſe
    -0.90
     juſt
    -0.89
     themſelves
    -0.88
     reaſon
    -0.88
     Efq
    -0.88
    POSITIVE LOGITS
    ↵
    0.40
    dtypes
    0.40
     and
    0.40
    ↵↵
    0.40
     Bra
    0.40
     disambiguazione
    0.40
     G
    0.38
     Ab
    0.38
    if
    0.38
    <bos>
    0.37
    Activations Density 0.112%

    No Known Activations