© 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. 1-CLT-HP
    7. 13170
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    <bos>
    -1.03
     betweenstory
    -0.77
     ModelExpression
    -0.77
    ########.
    -0.77
    ⓧ
    -0.73
    MENAFN
    -0.70
     يتيمه
    -0.66
    ✨:
    -0.64
    aarrggbb
    -0.64
    المكان
    -0.61
    POSITIVE LOGITS
    atile
    0.56
    hoga
    0.47
    stood
    0.47
    orithms
    0.46
    ISCH
    0.46
    pady
    0.45
    IDAE
    0.44
    eapple
    0.43
    '&:
    0.43
    tracks
    0.42
    Activations Density 0.097%

    No Known Activations