Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12158
    Prev
    Next
    INDEX
    Explanations

    good

    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
    good
    -0.79
     good
    -0.74
     bonne
    -0.65
    mybatisplus
    -0.60
    Good
    -0.60
     buena
    -0.55
     GOOD
    -0.53
    SharedCtor
    -0.52
     Good
    -0.52
    yntaxException
    -0.52
    POSITIVE LOGITS
     يتيمه
    0.63
    ControllerAdvice
    0.55
    \{\\
    0.53
    amitié
    0.52
    runOnUiThread
    0.52
    ).</
    0.52
    studies
    0.51
    makeText
    0.51
    Matters
    0.50
    )++;
    0.49
    Activations Density 0.009%

    No Known Activations