© 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. 13210
    Prev
    Next
    INDEX
    Explanations

    coding and names

    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
    e
    -0.60
    createComponent
    -0.50
    uid
    -0.47
    VersionUID
    -0.47
    r
    -0.45
     cư
    -0.45
    f
    -0.44
    т
    -0.43
    cks
    -0.43
    u
    -0.41
    POSITIVE LOGITS
    Personendaten
    1.02
    windowFixed
    0.82
    Tikang
    0.79
     يتيمه
    0.78
     tartalomajánló
    0.73
     transfieras
    0.73
     EconPapers
    0.71
    setVerticalGroup
    0.71
     Biôgrafia
    0.70
    يميديا
    0.68
    Activations Density 0.016%

    No Known Activations