© 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. 5-CLT-HP
    7. 95234
    Prev
    Next
    INDEX
    Explanations

    how

    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
     to
    -0.66
    arrête
    -0.56
     ourselves
    -0.54
     Comunicação
    -0.50
     davon
    -0.49
    ;"></
    -0.47
    Bibliografía
    -0.46
     sarili
    -0.45
    verband
    -0.45
     Мексичка
    -0.45
    POSITIVE LOGITS
     للاسماء
    0.72
    StoryboardSegue
    0.60
    RenderAtEndOf
    0.57
     BrowserModule
    0.56
    GOTREF
    0.56
    SerializedSize
    0.56
    enumii
    0.55
     EconPapers
    0.54
    فحة
    0.54
     PyTuple
    0.51
    Activations Density 0.000%

    No Known Activations