© 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. 77572
    Prev
    Next
    INDEX
    Explanations

    Foreign words

    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
    BuildContext
    -0.56
    __':
    -0.55
    addContainerGap
    -0.54
    CompilerServices
    -0.53
    ReferenceEquals
    -0.52
    %%
    -0.52
    zbęd
    -0.52
    اته
    -0.51
    Портал
    -0.50
    __))
    -0.50
    POSITIVE LOGITS
    出版年
    0.60
    ImageContext
    0.55
    VertexAttrib
    0.54
     verrez
    0.53
     récon
    0.52
     kuah
    0.52
    ViewImports
    0.50
     gez
    0.49
    providedIn
    0.48
     compréhen
    0.48
    Activations Density 0.007%

    No Known Activations