© 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. 72777
    Prev
    Next
    INDEX
    Explanations

    Technical, obscure text

    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
    PointerException
    -0.69
     BoxDecoration
    -0.61
     resourceCulture
    -0.55
    حياتها
    -0.52
    SupportActionBar
    -0.51
    مقاله
    -0.51
     Lut
    -0.50
     inf
    -0.50
    Msp
    -0.50
    greenrobot
    -0.50
    POSITIVE LOGITS
    TagMode
    0.68
    ValueStyle
    0.55
     '{@
    0.55
    SourceChecksum
    0.55
     COVERAGE
    0.51
    存于互联网档案馆
    0.48
     архивлан
    0.45
     fotografii
    0.45
    WebElementEntity
    0.44
    UserScript
    0.44
    Activations Density 0.000%

    No Known Activations