© 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. 4808
    Prev
    Next
    INDEX
    Explanations

    achievement of goals

    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
     uintptr
    -0.63
     للاسماء
    -0.54
    矶
    -0.52
    tagHelperRunner
    -0.51
     Handbuch
    -0.51
     /\.
    -0.51
    Revert
    -0.50
     يتيمه
    -0.49
     hairline
    -0.49
     connectivity
    -0.48
    POSITIVE LOGITS
    enumi
    0.66
    XmlAccessType
    0.56
     Exacts
    0.56
    исленность
    0.55
     Taktlose
    0.54
    jerg
    0.52
    TagMode
    0.50
     our
    0.49
     the
    0.48
    parsedMessage
    0.48
    Activations Density 0.002%

    No Known Activations