© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1400
    Prev
    Next
    INDEX
    Explanations

    as

    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
    Jeografia
    -0.77
    +#+#
    -0.73
    :+:
    -0.71
    batore
    -0.71
    Morfologia
    -0.69
    CppCodeGen
    -0.67
     <=",
    -0.65
    posedge
    -0.64
    mybatisplus
    -0.63
    SuppressMessage
    -0.63
    POSITIVE LOGITS
     wyda
    0.58
    strij
    0.48
     yaklaş
    0.46
     wydaje
    0.46
     scalars
    0.44
     theme
    0.44
     that
    0.44
     perspective
    0.44
    Resolve
    0.43
     darbu
    0.43
    Activations Density 0.001%

    No Known Activations