© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44164
    Prev
    Next
    INDEX
    Explanations

    finale

    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
    een
    -0.64
     asemenea
    -0.61
    e
    -0.60
     enfermera
    -0.59
     spéciaux
    -0.57
     bisog
    -0.56
    GraphicsUnit
    -0.56
    TagMode
    -0.55
     aikana
    -0.55
     ameste
    -0.55
    POSITIVE LOGITS
    soaked
    0.56
     Real
    0.54
    ük
    0.50
    AndEndTag
    0.50
    邃
    0.48
    ün
    0.48
    AlterField
    0.47
     Wild
    0.46
     <=",
    0.46
     drain
    0.45
    Activations Density 0.131%

    No Known Activations