© 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. 90933
    Prev
    Next
    INDEX
    Explanations

    machinery

    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
    ness
    -1.12
    iness
    -0.78
    ry
    -0.75
    inery
    -0.71
    acy
    -0.69
    son
    -0.68
    shire
    -0.67
    rary
    -0.66
    ation
    -0.65
    ship
    -0.64
    POSITIVE LOGITS
    rungsseite
    0.63
    tvguidetime
    0.63
    TypedDataSet
    0.63
    e
    0.60
     passaram
    0.55
     tiveram
    0.53
    evolution
    0.52
     culte
    0.52
     leçons
    0.52
    AutoresizingMask
    0.51
    Activations Density 0.099%

    No Known Activations