© 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. 44190
    Prev
    Next
    INDEX
    Explanations

    Ow

    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
     Diſ
    -0.84
     Reſ
    -0.79
     Anſ
    -0.78
    enumi
    -0.77
     Efq
    -0.75
    __':
    -0.75
     mijne
    -0.73
     surla
    -0.73
     Theſe
    -0.73
     ſtate
    -0.72
    POSITIVE LOGITS
    ver
    0.45
    __*/
    0.44
    To
    0.42
     To
    0.42
    при
    0.42
     Re
    0.42
    RestTemplate
    0.41
    to
    0.41
     Lo
    0.40
     visit
    0.39
    Activations Density 0.118%

    No Known Activations