© 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. 5-CLT-HP
    7. 92985
    Prev
    Next
    INDEX
    Explanations

    be

    np_max-act · 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
     '\\;'
    -0.58
    errHandler
    -0.54
    omitempty
    -0.51
    added
    -0.48
    NameInMap
    -0.48
     ErrIntOverflow
    -0.46
    windowFixed
    -0.45
     unknownFields
    -0.44
     Réponses
    -0.43
     added
    -0.42
    POSITIVE LOGITS
     perfectly
    0.66
     Offisielt
    0.65
    perfectly
    0.63
     Allí
    0.61
     tolerably
    0.60
     remarkably
    0.58
    ]='\
    0.57
     wonderfully
    0.57
     quite
    0.57
     Daar
    0.57
    Activations Density 0.004%

    No Known Activations