© 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. 4-CLT-HP
    7. 3511
    Prev
    Next
    INDEX
    Explanations

    Code, math, tech writing

    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>
    -0.83
    DockStyle
    -0.61
    addGap
    -0.54
     ||=
    -0.52
    ]")]
    -0.50
    webElement
    -0.48
     ThemeData
    -0.48
    djangoproject
    -0.46
    -,
    -0.46
    -\
    -0.45
    POSITIVE LOGITS
     doubtnut
    0.80
     Efq
    0.78
     kasarigan
    0.76
    TintMode
    0.69
     okuyayım
    0.69
     becauſe
    0.68
     Harrow
    0.68
     PWN
    0.67
    ########.
    0.66
     indépendant
    0.66
    Activations Density 0.024%

    No Known Activations