© 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. 4529
    Prev
    Next
    INDEX
    Explanations

    www

    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
    sizeCache
    -0.70
    "]));
    -0.63
    ())));
    -0.59
    Personensuche
    -0.59
     iprot
    -0.57
    "]];
    -0.56
    }`);
    -0.56
    ArrowToggle
    -0.55
     Chwiliwch
    -0.54
    Spoljašnje
    -0.53
    POSITIVE LOGITS
    opsida
    0.55
     WebDriverWait
    0.47
    *-*-
    0.47
    etcode
    0.46
    owna
    0.46
    oplan
    0.46
     sinon
    0.45
    ApiProperty
    0.44
    licité
    0.44
    étaire
    0.44
    Activations Density 0.003%

    No Known Activations