© 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. 4807
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     lenker
    -0.66
    ThroughAttribute
    -0.63
    Билгалдахарш
    -0.60
    hirt
    -0.55
     дописавши
    -0.54
     învă
    -0.52
     économies
    -0.52
    arela
    -0.51
     varför
    -0.51
     sélections
    -0.50
    POSITIVE LOGITS
     different
    0.82
    different
    0.67
    +:+
    0.65
    Different
    0.64
     Different
    0.64
     DIFFERENT
    0.60
     completely
    0.57
     Completely
    0.56
     separate
    0.55
     means
    0.55
    Activations Density 0.007%

    No Known Activations