© 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. 43952
    Prev
    Next
    INDEX
    Explanations

    visions

    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
     المعيارى
    -0.85
     تضيفلها
    -0.68
    stdc
    -0.67
     ErrIntOverflow
    -0.67
     térm
    -0.65
    ContentAsync
    -0.64
    Datuak
    -0.62
     importado
    -0.62
     tóxic
    -0.61
    UpInside
    -0.60
    POSITIVE LOGITS
    TResult
    0.50
     lo
    0.49
     gel
    0.47
    Autoritní
    0.47
     objective
    0.46
     opportunity
    0.46
     evidence
    0.46
     abstract
    0.45
     rever
    0.45
     provisional
    0.45
    Activations Density 0.077%

    No Known Activations