© 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. 45287
    Prev
    Next
    INDEX
    Explanations

    cardiovascular/graphite

    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
     volontaire
    -0.78
    CMOS
    -0.78
     HttpNotFound
    -0.77
     feroit
    -0.74
     auroit
    -0.73
     Teenage
    -0.71
     avoient
    -0.69
    StateToProps
    -0.69
     chrétienne
    -0.69
     dépens
    -0.68
    POSITIVE LOGITS
     actually
    0.42
     or
    0.40
    Raycast
    0.40
     im
    0.40
    ly
    0.40
     dem
    0.39
     and
    0.39
    zono
    0.38
    ,
    0.38
     en
    0.36
    Activations Density 0.025%

    No Known Activations