© 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. 5-CLT-HP
    7. 4503
    Prev
    Next
    INDEX
    Explanations

    Start of sentence/section

    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
     meaning
    -0.50
     OkHttpClient
    -0.50
     kav
    -0.47
     AppCompat
    -0.46
     WebDriverWait
    -0.46
     word
    -0.46
    Cursors
    -0.45
     derecho
    -0.45
    );"
    -0.44
     holding
    -0.43
    POSITIVE LOGITS
     nahilalakip
    0.75
    WillAppear
    0.69
     समीक्षाओं
    0.66
    ագրություններ
    0.65
    cshtml
    0.60
    Personensuche
    0.58
    tonode
    0.57
    říklad
    0.55
    labelledby
    0.54
    bootstrapcdn
    0.54
    Activations Density 0.000%

    No Known Activations