© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97266
    Prev
    Next
    INDEX
    Explanations

    contrasting statements

    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
    parsedMessage
    -0.70
    LElement
    -0.63
     становника
    -0.63
    KommentareTeilen
    -0.62
    this
    -0.55
     Partagez
    -0.54
    TypedDataSet
    -0.54
     "..\..\..\
    -0.54
     entanto
    -0.53
    WinForms
    -0.53
    POSITIVE LOGITS
    ArgsConstructor
    0.63
     VIAF
    0.54
    adecimal
    0.48
     >=",
    0.48
     Scale
    0.47
     setInterval
    0.47
    oprecip
    0.46
    krę
    0.45
     Vign
    0.45
     الحره
    0.45
    Activations Density 0.020%

    No Known Activations