© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96369
    Prev
    Next
    INDEX
    Explanations

    Describing physical attributes

    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
    MigrationBuilder
    -0.97
    ReusableCell
    -0.96
    AndEndTag
    -0.96
    parsedMessage
    -0.94
    uxxxx
    -0.91
     AssemblyCulture
    -0.88
    fjspx
    -0.87
    RenderAtEndOf
    -0.87
     Wikimedijinoj
    -0.82
     betweenstory
    -0.81
    POSITIVE LOGITS
    설
    0.42
     from
    0.39
    side
    0.38
    sikt
    0.38
     jas
    0.37
    leg
    0.37
    eyes
    0.36
    nos
    0.35
    ems
    0.35
     lateral
    0.35
    Activations Density 0.004%

    No Known Activations