© 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. 95215
    Prev
    Next
    INDEX
    Explanations

    programming descriptions

    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
     even
    -0.89
     siquiera
    -0.78
    even
    -0.78
     nor
    -0.73
     ever
    -0.72
     réellement
    -0.69
     ogóle
    -0.69
    จริงๆ
    -0.68
     même
    -0.68
    ever
    -0.68
    POSITIVE LOGITS
    libft
    0.56
     enjoyed
    0.54
     experience
    0.54
     FetchType
    0.50
     createSprite
    0.49
    XmlAccessorType
    0.49
     enjoy
    0.47
    TemporalType
    0.47
     defaultstate
    0.46
     benefit
    0.43
    Activations Density 0.002%

    No Known Activations