© 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. 5-CLT-HP
    7. 2050
    Prev
    Next
    INDEX
    Explanations

    standardization

    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
    windowFixed
    -0.70
     NACA
    -0.69
     TestBed
    -0.68
     resourceCulture
    -0.68
    Geografi
    -0.66
    ScopeManager
    -0.66
     surla
    -0.65
     BorderRadius
    -0.65
     himſelf
    -0.65
     дописавши
    -0.64
    POSITIVE LOGITS
     on
    0.77
     upon
    0.60
     how
    0.50
     على
    0.49
     notes
    0.48
     UPON
    0.47
     all
    0.46
     ON
    0.46
     guardia
    0.46
     calculations
    0.45
    Activations Density 0.004%

    No Known Activations