© 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. 92042
    Prev
    Next
    INDEX
    Explanations

    flag

    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
    Flag
    -0.60
     Flag
    -0.60
     flag
    -0.59
    List
    -0.52
    flag
    -0.52
     List
    -0.52
    BIE
    -0.49
     Flags
    -0.46
    Flags
    -0.43
    arvi
    -0.43
    POSITIVE LOGITS
     AssemblyCompany
    0.73
    PreferredItem
    0.64
    lossians
    0.61
     Pythag
    0.61
    parsedMessage
    0.59
    ifolia
    0.58
    fight
    0.57
    makers
    0.55
    peka
    0.55
    hpur
    0.55
    Activations Density 0.056%

    No Known Activations