© 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. 3315
    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
    ########.
    -0.48
    pakatan
    -0.47
     early
    -0.46
     focused
    -0.46
     customers
    -0.45
     unit
    -0.45
     units
    -0.45
     shoppers
    -0.44
     quote
    -0.43
    ூர்
    -0.43
    POSITIVE LOGITS
    InputBorder
    0.77
    LEncoder
    0.61
    脚注の使い方
    0.57
    DOCTYPE
    0.57
    Pranala
    0.56
     Tash
    0.54
    AddHtmlAttribute
    0.53
    TagMode
    0.52
    AxisAlignment
    0.52
    maakt
    0.52
    Activations Density 0.011%

    No Known Activations