© 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. 20-CLT-HP
    7. 74552
    Prev
    Next
    INDEX
    Explanations

    Technical language

    np_max-act-logits · 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
    lag
    -0.52
    lagen
    -0.50
    nls
    -0.49
    gra
    -0.48
    llo
    -0.48
     nahilalakip
    -0.47
    graph
    -0.46
    ctomy
    -0.45
    kiat
    -0.44
    DateTimeFormat
    -0.44
    POSITIVE LOGITS
    EndContext
    0.68
     unknownFields
    0.58
    tagext
    0.54
     StringTokenizer
    0.54
     MemoryStream
    0.53
     bpy
    0.53
     Reihen
    0.52
     himo
    0.52
    Hentet
    0.51
    المناصب
    0.51
    Activations Density 0.015%

    No Known Activations