© 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. 45078
    Prev
    Next
    INDEX
    Explanations

    us

    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
     us
    -0.87
     them
    -0.80
    themselves
    -0.78
    them
    -0.76
     THEM
    -0.72
    Them
    -0.69
     themselves
    -0.68
     Them
    -0.67
     yourselves
    -0.67
    endpush
    -0.67
    POSITIVE LOGITS
    extAlignment
    0.63
    makeConstraints
    0.59
     متعلقه
    0.54
    ConstraintMaker
    0.52
    Rüyada
    0.49
    AddTagHelper
    0.45
     grammi
    0.45
     StatefulWidget
    0.45
    ArgsConstructor
    0.44
     estekak
    0.44
    Activations Density 0.100%

    No Known Activations