© 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. 20-CLT-HP
    7. 76973
    Prev
    Next
    INDEX
    Explanations

    struggling

    np_max-act-logits · 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
    новништво
    -0.68
    Билгалдахарш
    -0.63
     Wiktionnaire
    -0.62
    Tazama
    -0.62
     Sociales
    -0.61
    itinéraire
    -0.60
     виправивши
    -0.60
     Meilleur
    -0.59
     Púb
    -0.59
    DotNetBar
    -0.58
    POSITIVE LOGITS
    Controlling
    0.47
    lccn
    0.46
    orance
    0.41
     moder
    0.41
     raising
    0.39
     managing
    0.39
    Raising
    0.39
     controlling
    0.38
    reebok
    0.38
    __*/
    0.38
    Activations Density 0.001%

    No Known Activations