© 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. 92063
    Prev
    Next
    INDEX
    Explanations

    letters and related

    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
    awtextra
    -0.72
     الرياضيه
    -0.65
    MigrationBuilder
    -0.63
     fonts
    -0.60
    Kariera
    -0.60
    òa
    -0.59
     Dandy
    -0.59
    oredCriteria
    -0.57
     sherds
    -0.56
    TagHelper
    -0.56
    POSITIVE LOGITS
    FTFY
    0.55
    日閲覧
    0.49
    RTEE
    0.46
     חיצוניים
    0.44
     ?>>
    0.42
    uté
    0.42
    ⏟
    0.42
    lasia
    0.41
     human
    0.41
     kaynağından
    0.41
    Activations Density 0.103%

    No Known Activations