© 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. 76477
    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
    ContentAlignment
    -0.86
    makeConstraints
    -0.72
    Personendaten
    -0.66
     AssemblyProduct
    -0.61
     ArrayAdapter
    -0.60
     Erişim
    -0.60
    urlopen
    -0.60
     Roskov
    -0.57
    errHandler
    -0.57
     MainAxisSize
    -0.56
    POSITIVE LOGITS
     préoccup
    0.49
    ValueStyle
    0.46
    GeneratedMessage
    0.44
     blanches
    0.43
     hayas
    0.43
     élas
    0.42
    setof
    0.42
     végét
    0.41
     tiens
    0.41
     tasche
    0.41
    Activations Density 0.000%

    No Known Activations