© 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. 5-CLT-HP
    7. 1967
    Prev
    Next
    INDEX
    Explanations

    members

    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
    DoubleQuotes
    -0.46
     doInBackground
    -0.43
     channels
    -0.43
     bottles
    -0.43
     pockets
    -0.43
     pathogenesis
    -0.41
    hd
    -0.41
     Coleoptera
    -0.41
    Portály
    -0.41
     bottle
    -0.41
    POSITIVE LOGITS
    Personendaten
    0.90
     >=",
    0.86
     متعلقه
    0.73
    enumi
    0.72
    MessageOf
    0.72
    Personensuche
    0.69
     jScrollPane
    0.65
    AndEndTag
    0.63
     تضيفلها
    0.61
     ***!
    0.60
    Activations Density 0.001%

    No Known Activations