© 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. 20-CLT-HP
    7. 75013
    Prev
    Next
    INDEX
    Explanations

    Academic texts

    np_max-act-logits · 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
    -0.80
    providing
    -0.68
     providing
    -0.68
     containing
    -0.68
     totalling
    -0.67
     समीक्षक
    -0.67
     саны
    -0.66
     suggesting
    -0.66
    SharedCtor
    -0.66
    Providing
    -0.65
    POSITIVE LOGITS
    Kontrola
    0.64
     nargin
    0.51
     isKindOfClass
    0.51
    PDU
    0.47
     cover
    0.45
     hydrophobic
    0.45
     }}{
    0.45
    esterday
    0.44
     drumming
    0.44
     Dancing
    0.44
    Activations Density 0.001%

    No Known Activations