© 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. 1-CLT-HP
    7. 12274
    Prev
    Next
    INDEX
    Explanations

    PD

    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
    PD
    -1.56
     PD
    -1.10
    pd
    -1.02
     pd
    -0.73
     cradle
    -0.63
    Pd
    -0.60
     Cradle
    -0.59
    PDS
    -0.57
    پیوند
    -0.57
     BPD
    -0.54
    POSITIVE LOGITS
    invokeLater
    0.65
    xase
    0.57
    IntoConstraints
    0.56
     Eſ
    0.55
     Efq
    0.54
    ніципалі
    0.54
    (||
    0.54
     mobilisation
    0.53
    InvalidProtocol
    0.53
     Herv
    0.53
    Activations Density 0.050%

    No Known Activations