© 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. 20-CLT-HP
    7. 74751
    Prev
    Next
    INDEX
    Explanations

    names and places

    np_max-act-logits · 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
    ANTO
    -0.56
    akin
    -0.56
    anto
    -0.55
    aq
    -0.53
    oglo
    -0.53
    GER
    -0.52
    enumi
    -0.52
     tong
    -0.51
    hagen
    -0.50
    StringWriter
    -0.50
    POSITIVE LOGITS
     AssemblyCulture
    0.81
    ViewFeatures
    0.58
    ural
    0.56
    PreferredItem
    0.56
    cerely
    0.55
     exemplaires
    0.53
    ModelSerializer
    0.52
     démocr
    0.52
     operações
    0.51
    parsedMessage
    0.50
    Activations Density 0.001%

    No Known Activations