Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74238
    Prev
    Next
    INDEX
    Explanations

    Level

    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
    IContainer
    -0.82
     nahilalakip
    -0.75
    UrlResolution
    -0.70
    Xna
    -0.66
    EDEFAULT
    -0.66
    fromnode
    -0.64
    posedge
    -0.63
     MainAxisSize
    -0.63
    JspWriter
    -0.61
    MLLoader
    -0.61
    POSITIVE LOGITS
     level
    1.02
     levels
    0.88
     spirit
    0.82
     plumb
    0.79
    level
    0.79
     LEVEL
    0.77
     Level
    0.74
     уров
    0.72
    levels
    0.71
     nivel
    0.71
    Activations Density 0.000%

    No Known Activations