© 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. 92024
    Prev
    Next
    INDEX
    Explanations

    of

    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
    SizeF
    -0.68
     Eura
    -0.58
     seat
    -0.57
    +#+#
    -0.56
    TagHelper
    -0.55
     cdti
    -0.54
    StoryboardSegue
    -0.54
     TType
    -0.54
    /**
    -0.54
    ')")
    -0.54
    POSITIVE LOGITS
     CreateTagHelper
    0.60
     bitten
    0.52
    RectangleBorder
    0.51
    ConstraintMaker
    0.51
    ecraft
    0.50
    gypti
    0.49
    jsonwebtoken
    0.49
     insuffisamment
    0.49
    ftan
    0.48
    fillColor
    0.48
    Activations Density 0.155%

    No Known Activations