© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97634
    Prev
    Next
    INDEX
    Explanations

    exposure/assumption

    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
     exposure
    -0.71
     étoient
    -0.71
     avoient
    -0.71
     chré
    -0.67
     démocr
    -0.66
     enfans
    -0.60
     ainfi
    -0.59
     extérieures
    -0.59
     vertes
    -0.57
    iness
    -0.54
    POSITIVE LOGITS
     EconPapers
    0.77
    sizeCache
    0.68
    LookAnd
    0.66
    IndentedString
    0.61
    Bism
    0.58
    lectic
    0.56
    rungsseite
    0.55
    Демографія
    0.53
    thâu
    0.52
    tagHelperRunner
    0.52
    Activations Density 0.040%

    No Known Activations