© 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. 77564
    Prev
    Next
    INDEX
    Explanations

    say "How"

    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
     surla
    -0.70
     Италијани
    -0.68
    Portale
    -0.67
     betweenstory
    -0.65
    SourceChecksum
    -0.61
    AnchorStyles
    -0.60
    numerusform
    -0.60
    RefNanny
    -0.60
    Rüyada
    -0.59
    Diwedd
    -0.59
    POSITIVE LOGITS
     H
    0.50
     Why
    0.45
     Hv
    0.43
     About
    0.43
     How
    0.41
    specialchars
    0.40
    inguishing
    0.40
     W
    0.40
     Against
    0.39
     Whatever
    0.39
    Activations Density 0.004%

    No Known Activations