© 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. 4-CLT-HP
    7. 3423
    Prev
    Next
    INDEX
    Explanations

    Sentence end

    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
     للاسماء
    -0.87
    UnusedPrivate
    -0.86
    (!__
    -0.86
    Personensuche
    -0.79
    principalTable
    -0.77
     defaultstate
    -0.72
    ConstraintMaker
    -0.69
     PyLong
    -0.68
     saites
    -0.68
    Rüyada
    -0.68
    POSITIVE LOGITS
     Method
    0.41
    </thead>
    0.40
     Runtime
    0.39
    IAS
    0.37
     Greater
    0.37
     erleich
    0.37
     atas
    0.35
     Access
    0.35
    bati
    0.35
     okuyayım
    0.34
    Activations Density 0.001%

    No Known Activations