© 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. 91062
    Prev
    Next
    INDEX
    Explanations

    time

    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
    a
    -0.50
    p
    -0.49
     U
    -0.48
     P
    -0.42
     modern
    -0.42
    x
    -0.41
     van
    -0.40
    rid
    -0.39
     PM
    -0.39
    estro
    -0.39
    POSITIVE LOGITS
     Мексичка
    1.00
     myſelf
    0.99
     pleaſure
    0.96
    IntoConstraints
    0.96
     itſelf
    0.93
     faſt
    0.93
     houſe
    0.91
     Houſe
    0.90
     whoſe
    0.90
     ſeveral
    0.89
    Activations Density 0.215%

    No Known Activations