© 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. 93079
    Prev
    Next
    INDEX
    Explanations

    are

    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
    Зноскі
    -0.68
    setVerticalGroup
    -0.66
    fromnode
    -0.66
    Izvori
    -0.64
    AndEndTag
    -0.64
    Tembelea
    -0.63
    rrggbb
    -0.60
    Véxase
    -0.59
    Referencies
    -0.59
    Lähteet
    -0.59
    POSITIVE LOGITS
     aceton
    0.52
     iub
    0.49
     seafood
    0.49
     eukaryotic
    0.47
    utiva
    0.47
     cashmere
    0.47
     circumcision
    0.47
     quiche
    0.47
     sulph
    0.46
     sequestration
    0.46
    Activations Density 0.000%

    No Known Activations