© 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. 5-CLT-HP
    7. 26
    Prev
    Next
    INDEX
    Explanations

    to

    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
     resourceCulture
    -0.53
    Демографія
    -0.53
    Uris
    -0.52
    ágot
    -0.51
     threefold
    -0.51
     Greet
    -0.50
    SourceChecksum
    -0.50
    yntaxException
    -0.49
     <<<
    -0.48
    CodeAttribute
    -0.48
    POSITIVE LOGITS
     our
    0.82
     its
    0.75
     those
    0.75
     their
    0.73
     the
    0.73
     all
    0.73
     your
    0.67
     ourselves
    0.63
    olume
    0.63
     everyone
    0.59
    Activations Density 0.000%

    No Known Activations