© 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. 4-CLT-HP
    7. 1929
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
     nahilalakip
    -0.82
    LabelTagHelper
    -0.57
     للمعارف
    -0.57
    RenderAtEndOf
    -0.57
     nakalista
    -0.53
    makeConstraints
    -0.52
     Biôgrafia
    -0.52
    StoryboardSegue
    -0.50
    eterangan
    -0.50
     OFDb
    -0.50
    POSITIVE LOGITS
    atics
    0.59
    rull
    0.56
    HasAnnotation
    0.53
     artísticas
    0.52
     actuels
    0.50
     normaux
    0.49
    กก
    0.49
     idées
    0.49
     NKC
    0.48
     thérape
    0.48
    Activations Density 0.003%

    No Known Activations