© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72192
    Prev
    Next
    INDEX
    Explanations

    URLs and code

    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
     avoient
    -0.68
     varandra
    -0.68
     étoit
    -0.64
    __*/
    -0.63
     auroit
    -0.61
     móveis
    -0.60
     kvinna
    -0.60
    ckså
    -0.59
     kvinder
    -0.59
     étoient
    -0.58
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.62
    SuppressMessage
    0.62
     Wikispecies
    0.61
    といけない
    0.60
     some
    0.60
     favourable
    0.59
    autoconfigure
    0.57
     rather
    0.57
     fairly
    0.56
     mild
    0.56
    Activations Density 0.001%

    No Known Activations