© 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. 5651
    Prev
    Next
    INDEX
    Explanations

    wound

    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
     Predicting
    -0.48
     Digital
    -0.47
     zb
    -0.47
    OGND
    -0.46
    Digital
    -0.46
     predicting
    -0.46
    .”
    -0.45
    AddHtmlAttribute
    -0.45
     digital
    -0.44
     بذلك
    -0.44
    POSITIVE LOGITS
    læg
    0.65
     nakalista
    0.61
     pulumi
    0.61
    Personendaten
    0.60
    PTT
    0.59
    Rhestr
    0.59
     nemlig
    0.58
    adaptiveStyles
    0.58
    enterOuterAlt
    0.58
    WebElementEntity
    0.57
    Activations Density 0.060%

    No Known Activations