© 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. 1-CLT-HP
    7. 46069
    Prev
    Next
    INDEX
    Explanations

    ting

    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
    SourceChecksum
    -0.49
    发表于
    -0.49
    urnum
    -0.47
     vorstellen
    -0.46
    GenerationType
    -0.46
    attendre
    -0.45
    literals
    -0.44
    enterOuterAlt
    -0.44
     local
    -0.43
     détails
    -0.43
    POSITIVE LOGITS
     AssemblyCulture
    0.99
    InMillis
    0.64
    databind
    0.61
     Velo
    0.58
     Medals
    0.56
     Muc
    0.55
     Worms
    0.55
    Rohy
    0.55
     BOC
    0.54
    CloseOperation
    0.53
    Activations Density 0.008%

    No Known Activations