© 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. 1-CLT-HP
    7. 510
    Prev
    Next
    INDEX
    Explanations

    to

    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
    tvguidetime
    -0.95
    RenderAtEndOf
    -0.90
     snippetHide
    -0.80
     nakalista
    -0.79
     AssemblyCulture
    -0.78
    Geplaatst
    -0.75
    abestanden
    -0.73
     Normdatei
    -0.68
    AndEndTag
    -0.68
    rrggbb
    -0.67
    POSITIVE LOGITS
     form
    0.63
    produce
    0.56
     повіт
    0.52
    mainen
    0.52
     produce
    0.51
    yield
    0.51
    form
    0.51
    Produce
    0.50
    तु
    0.50
    Make
    0.47
    Activations Density 0.017%

    No Known Activations