Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73902
    Prev
    Next
    INDEX
    Explanations

    to

    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
    BagConstraints
    -0.59
    farwyddwr
    -0.51
    agent
    -0.51
    GenerationType
    -0.49
    OCCURRED
    -0.48
    killer
    -0.48
     uska
    -0.48
     surla
    -0.47
    jores
    -0.47
    WebElementEntity
    -0.47
    POSITIVE LOGITS
    ting
    0.82
    ssing
    0.81
    eing
    0.71
    tting
    0.70
    ts
    0.68
    othed
    0.62
    tes
    0.60
    bbing
    0.60
    sser
    0.58
    mbo
    0.56
    Activations Density 0.003%

    No Known Activations