© 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. 3919
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     he
    -0.46
     opleiding
    -0.45
    bootstrapcdn
    -0.44
    photobucket
    -0.44
     refroid
    -0.43
    he
    -0.42
     in
    -0.41
     hırka
    -0.41
     dépla
    -0.40
     mình
    -0.40
    POSITIVE LOGITS
    titleMargin
    0.66
     myſelf
    0.66
     Савезне
    0.63
    bernate
    0.63
    OutputPath
    0.62
     كومونز
    0.62
    ímite
    0.58
    ussis
    0.57
     fhew
    0.57
     EClass
    0.57
    Activations Density 0.002%

    No Known Activations