© 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. 4-CLT-HP
    7. 4301
    Prev
    Next
    INDEX
    Explanations

    up

    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
    kloped
    -0.81
    enumi
    -0.80
    AndEndTag
    -0.75
     resourceCulture
    -0.74
    adaptiveStyles
    -0.72
    rededor
    -0.70
    enumii
    -0.69
    TagMode
    -0.68
     المعيارى
    -0.66
     وتسجيلات
    -0.65
    POSITIVE LOGITS
     handling
    0.59
     playing
    0.51
     spotting
    0.50
     Throwable
    0.48
     bringing
    0.47
     offering
    0.47
     making
    0.47
    adra
    0.45
     riding
    0.44
     additional
    0.43
    Activations Density 0.004%

    No Known Activations