© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71979
    Prev
    Next
    INDEX
    Explanations

    Code and uncommon words

    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
     <=",
    -0.54
    ẨM
    -0.46
     مرئيه
    -0.46
    ToBounds
    -0.44
    kras
    -0.43
     '\\;'
    -0.42
     trails
    -0.42
     liz
    -0.41
    WebVitals
    -0.40
    دانشنامهٔ
    -0.40
    POSITIVE LOGITS
     propOrder
    0.58
    rowing
    0.54
     crossing
    0.52
     PPR
    0.51
    ChromeDriver
    0.51
     autorytatywna
    0.51
    AppMethodBeat
    0.50
    setArguments
    0.49
     Severn
    0.49
    gage
    0.48
    Activations Density 0.002%

    No Known Activations