© 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. 4-CLT-HP
    7. 833
    Prev
    Next
    INDEX
    Explanations

    mand

    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
     GenerationType
    -0.58
    ThroughAttribute
    -0.52
    Para
    -0.48
    fieldId
    -0.47
    para
    -0.46
     Пара
    -0.46
    orgi
    -0.46
    InstanceState
    -0.45
     сбо
    -0.45
     Para
    -0.44
    POSITIVE LOGITS
     CreateTagHelper
    0.79
     مشين
    0.76
    脚注の使い方
    0.69
    Filmographie
    0.61
    ."</
    0.59
    simov
    0.56
     tslint
    0.56
    enapa
    0.56
    Lähteet
    0.56
    liferay
    0.56
    Activations Density 0.005%

    No Known Activations