© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4982
    Prev
    Next
    INDEX
    Explanations

    escape

    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
    ducers
    -0.51
     actionMode
    -0.46
    setOnAction
    -0.45
    ніципалі
    -0.44
    POC
    -0.43
    diad
    -0.43
    strains
    -0.43
    gini
    -0.42
     initiate
    -0.42
    ngths
    -0.42
    POSITIVE LOGITS
    MessageOf
    0.76
    GraphicsUnit
    0.70
    الإنجليزية
    0.65
     متعلقه
    0.57
    TagHelper
    0.56
     retiring
    0.55
    Становништво
    0.55
    χε
    0.54
     Reverso
    0.54
    ReusableCell
    0.53
    Activations Density 0.004%

    No Known Activations