© 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. 0-CLT-HP
    7. 42574
    Prev
    Next
    INDEX
    Explanations

    replacing

    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
     replacement
    -1.34
     Replacement
    -1.31
     replaces
    -1.28
    replacing
    -1.27
     replacing
    -1.23
    Replacement
    -1.20
    replacement
    -1.18
     replace
    -1.17
     Replacing
    -1.15
    Replacing
    -1.11
    POSITIVE LOGITS
    GEBURTSDATUM
    0.97
     betweenstory
    0.86
     AssemblyCulture
    0.74
    parsedMessage
    0.73
     beginnetje
    0.71
    قایناق‌لار
    0.70
    IVEREF
    0.68
    verwijspagina
    0.68
    UserScript
    0.68
    transQ
    0.66
    Activations Density 0.075%

    No Known Activations