© 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. 3827
    Prev
    Next
    INDEX
    Explanations

    quote marks

    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
    Datuak
    -0.90
    +#+#
    -0.86
    __(/*!
    -0.80
     nakalista
    -0.80
     ligiloj
    -0.79
     autorytatywna
    -0.77
    expandindo
    -0.77
    /******/
    -0.77
     unknownFields
    -0.76
    setVerticalGroup
    -0.76
    POSITIVE LOGITS
     He
    0.49
     fallu
    0.45
     öppna
    0.44
     snart
    0.41
     varandra
    0.39
     ouverts
    0.39
     gärna
    0.39
     barnen
    0.37
     öpp
    0.37
     finnas
    0.37
    Activations Density 0.008%

    No Known Activations