© 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. 72874
    Prev
    Next
    INDEX
    Explanations

    Code and foreign languages

    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
     дописавши
    -0.71
    PRD
    -0.63
     ErrIntOverflow
    -0.62
    setVerticalGroup
    -0.61
    ########.
    -0.61
    tagHelperRunner
    -0.57
    UnknownFieldSet
    -0.57
    px
    -0.52
    UnsafeEnabled
    -0.52
    opress
    -0.52
    POSITIVE LOGITS
    PerformLayout
    0.74
     سكانية
    0.56
    basicConfig
    0.54
    <caption>
    0.53
     onOptions
    0.48
    setContentType
    0.47
     мәкал
    0.45
    Hentet
    0.43
    SPJ
    0.43
    ernas
    0.43
    Activations Density 0.006%

    No Known Activations