© 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. 5-CLT-HP
    7. 4957
    Prev
    Next
    INDEX
    Explanations

    established

    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
    Enllaces
    -0.62
    kepada
    -0.54
    NUMX
    -0.54
     ModelExpression
    -0.53
    ագրություններ
    -0.52
     GENERATED
    -0.52
    FXMLLoader
    -0.51
    hared
    -0.50
    HomeAsUpEnabled
    -0.50
    TagMode
    -0.50
    POSITIVE LOGITS
     Loomis
    0.53
     marry
    0.49
     Chum
    0.48
    wnątrz
    0.47
     spea
    0.45
     Adriana
    0.44
    Trax
    0.44
     Preacher
    0.44
    .*")]
    0.44
    Trama
    0.44
    Activations Density 0.000%

    No Known Activations