© 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. 1-CLT-HP
    7. 15451
    Prev
    Next
    INDEX
    Explanations

    medical and scientific

    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
    帖最后由
    -0.74
    aarrggbb
    -0.72
    CppMethod
    -0.68
    GEBURTSDATUM
    -0.66
    Gön
    -0.65
    WriteTagHelper
    -0.63
    Hozzáférés
    -0.61
    -------------</
    -0.60
    complexContent
    -0.58
    tvguidetime
    -0.58
    POSITIVE LOGITS
    /.../
    0.55
    /');
    0.51
     -->>
    0.49
    ')(
    0.47
    ctibles
    0.45
    ixeira
    0.45
    ,....
    0.45
    }\|
    0.44
    ();)
    0.44
    ItemBackground
    0.44
    Activations Density 0.010%

    No Known Activations