© 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. 1-CLT-HP
    7. 12995
    Prev
    Next
    INDEX
    Explanations

    track

    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
    track
    -0.70
     tracking
    -0.62
     track
    -0.62
     Track
    -0.61
    Track
    -0.59
    Népesség
    -0.59
     TRACK
    -0.57
    tracking
    -0.55
    hoeddwyd
    -0.54
     Tracking
    -0.53
    POSITIVE LOGITS
    BeginInit
    0.58
     noqa
    0.55
    InvalidProtocol
    0.54
    hmig
    0.52
    一道
    0.51
    cets
    0.50
    DockStyle
    0.50
     Serializable
    0.50
    iak
    0.49
    acic
    0.49
    Activations Density 0.101%

    No Known Activations