© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75724
    Prev
    Next
    INDEX
    Explanations

    Non-English/code tokens

    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
    IsContent
    -0.69
     estekak
    -0.67
    enumii
    -0.65
    脚注の使い方
    -0.61
    GIH
    -0.60
    hamshire
    -0.59
    MLLoader
    -0.58
    tvguidetime
    -0.58
    nthetic
    -0.57
    oredCriteria
    -0.57
    POSITIVE LOGITS
     //$
    0.44
     tud
    0.43
    軋
    0.42
    ++]=
    0.42
    خصة
    0.41
    UGAL
    0.41
    ConstraintMaker
    0.40
    новништво
    0.40
     emperador
    0.40
    producción
    0.40
    Activations Density 0.005%

    No Known Activations