© 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. 42314
    Prev
    Next
    INDEX
    Explanations

    technical/scientific contexts

    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
     dc
    -0.77
     DC
    -0.71
    ticularly
    -0.63
     समीक्षक
    -0.59
    ítmény
    -0.59
     Dc
    -0.57
    ধ্য
    -0.57
    maic
    -0.56
     виправивши
    -0.55
    öny
    -0.55
    POSITIVE LOGITS
    TagHelper
    0.56
    ViewFeatures
    0.56
    ритори
    0.54
    setopt
    0.53
     Référence
    0.52
    InvalidProtocol
    0.51
    MLLoader
    0.50
    帖最后由
    0.50
    Referències
    0.50
    Referanser
    0.50
    Activations Density 1.567%

    No Known Activations