© 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. 0-CLT-HP
    7. 45179
    Prev
    Next
    INDEX
    Explanations

    selection process

    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
    pilot
    -0.95
    draft
    -0.88
    Pilot
    -0.80
     draft
    -0.77
    a
    -0.76
    i
    -0.71
    ی
    -0.71
     pilot
    -0.71
     Pilot
    -0.69
     pilote
    -0.64
    POSITIVE LOGITS
     Conſ
    0.73
    selves
    0.64
     saites
    0.63
     ―――――
    0.62
     setLoading
    0.60
     Monfieur
    0.58
    ſelves
    0.58
     Reſ
    0.57
    parsedMessage
    0.57
     swo
    0.56
    Activations Density 0.748%

    No Known Activations