© 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. 0-CLT-HP
    7. 42830
    Prev
    Next
    INDEX
    Explanations

    various topics

    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
     виправивши
    -0.60
    findpost
    -0.56
    HomeAsUpEnabled
    -0.54
    salms
    -0.52
     समीक्षक
    -0.52
     Arie
    -0.52
    UnifiedTopology
    -0.50
     armband
    -0.49
     Elvira
    -0.48
     Theſe
    -0.48
    POSITIVE LOGITS
    MessageTagHelper
    0.57
    ControllerAdvice
    0.51
    MLLoader
    0.47
    magma
    0.47
    glement
    0.47
     fleste
    0.46
    idjan
    0.45
    lamabad
    0.45
     Sample
    0.45
     Bur
    0.44
    Activations Density 0.105%

    No Known Activations