© 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. 45262
    Prev
    Next
    INDEX
    Explanations

    time units

    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
    OfWork
    -0.69
     iconFacebook
    -0.65
    envolvimento
    -0.64
     spéciaux
    -0.63
     toepassing
    -0.63
     ddelweddau
    -0.61
     générations
    -0.61
     vieill
    -0.60
     synthèse
    -0.59
     lecteurs
    -0.59
    POSITIVE LOGITS
     the
    0.56
    elemField
    0.55
    hores
    0.52
    ctrica
    0.52
     taps
    0.51
    orious
    0.50
    Carriera
    0.50
    bitField
    0.49
    estroyer
    0.48
    edonian
    0.48
    Activations Density 0.075%

    No Known Activations