© 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. 97637
    Prev
    Next
    INDEX
    Explanations

    embra

    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
    fromnode
    -0.87
    pora
    -0.82
    Tembelea
    -0.81
     Waray
    -0.79
    uted
    -0.75
    windowFixed
    -0.75
     touched
    -0.75
    󠁴
    -0.74
    RTDA
    -0.73
     تضيفلها
    -0.73
    POSITIVE LOGITS
    PASSED
    0.49
     bel
    0.47
    urlencoded
    0.46
     spel
    0.45
    prepareStatement
    0.44
     pa
    0.42
     to
    0.41
     miss
    0.41
     mano
    0.41
     lead
    0.41
    Activations Density 0.054%

    No Known Activations