© 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. 13079
    Prev
    Next
    INDEX
    Explanations

    spread

    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
    XmlAccessType
    -0.90
     spread
    -0.88
    Spread
    -0.84
     Spread
    -0.81
    spread
    -0.81
    oa̍t
    -0.71
     arşivlendi
    -0.64
    LayoutStyle
    -0.63
    VersionUID
    -0.62
    StoryboardSegue
    -0.59
    POSITIVE LOGITS
     noisy
    0.47
     tetrachloride
    0.46
     Nhật
    0.45
    calientes
    0.44
     naph
    0.43
     createState
    0.42
     vibration
    0.41
     Henning
    0.41
     fiat
    0.41
     trembling
    0.40
    Activations Density 0.025%

    No Known Activations