© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11802
    Prev
    Next
    INDEX
    Explanations

    MEMS

    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
    '}';
    -0.61
    rawDesc
    -0.61
    posedge
    -0.59
    ToBounds
    -0.57
    Kaynakça
    -0.54
     مشين
    -0.53
     AssemblyCulture
    -0.52
    Jig
    -0.52
    mergeFrom
    -0.50
    WriteBarrier
    -0.50
    POSITIVE LOGITS
    Walls
    0.61
     Theſe
    0.56
     Walls
    0.54
    GIVEREF
    0.54
     Gaia
    0.54
    EXPRESSION
    0.54
    PROCESSING
    0.53
     estekak
    0.52
     conversion
    0.52
    ſelf
    0.52
    Activations Density 0.021%

    No Known Activations