© 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. 13032
    Prev
    Next
    INDEX
    Explanations

    am

    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
     termica
    -0.59
    gonic
    -0.59
     gärna
    -0.57
    mergeFrom
    -0.55
     dentaire
    -0.54
     Argentino
    -0.53
    AsUp
    -0.52
     censiti
    -0.51
    FieldBuilder
    -0.50
     owes
    -0.50
    POSITIVE LOGITS
    ikin
    0.59
     كومونز
    0.58
    httphttps
    0.56
    hoid
    0.56
     تضيفلها
    0.55
    TagHelper
    0.52
    Халык
    0.51
     chi̍t
    0.50
    Legături
    0.50
    VersionUID
    0.49
    Activations Density 0.030%

    No Known Activations