© 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. 97525
    Prev
    Next
    INDEX
    Explanations

    a

    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
     tri
    -0.56
     ant
    -0.55
     in
    -0.54
     arm
    -0.54
     art
    -0.53
     en
    -0.51
     a
    -0.50
    cra
    -0.49
     op
    -0.48
     av
    -0.48
    POSITIVE LOGITS
    parsedMessage
    0.94
     Monfieur
    0.92
    انجليز
    0.87
     alimentaires
    0.84
    elemField
    0.84
     Shakspeare
    0.82
     wireType
    0.82
     Houſe
    0.81
    DockStyle
    0.81
     réfrig
    0.81
    Activations Density 0.081%

    No Known Activations