© 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. 2491
    Prev
    Next
    INDEX
    Explanations

    code

    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
    umab
    -0.59
    自己在
    -0.46
     üzere
    -0.45
    lindungan
    -0.44
    matchCondition
    -0.44
     ModelExpression
    -0.44
     getP
    -0.44
     opérateur
    -0.43
    pted
    -0.43
     simplifié
    -0.42
    POSITIVE LOGITS
     unknownFields
    0.77
     propOrder
    0.63
     EdgeInsets
    0.63
     strconv
    0.59
     androidx
    0.56
    raisemb
    0.56
     lenker
    0.54
    onAttach
    0.53
    المكان
    0.52
    SocketAddress
    0.52
    Activations Density 0.001%

    No Known Activations