© 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. 2313
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    StructEnd
    -0.73
     MainAxisSize
    -0.71
     resourceCulture
    -0.68
     hostages
    -0.65
     insuffisamment
    -0.65
    StoreMessageInfo
    -0.64
     للاسماء
    -0.63
    __(/*!
    -0.62
    TProtocol
    -0.61
     AppModule
    -0.60
    POSITIVE LOGITS
    Rhestr
    0.44
     Wer
    0.43
     Insee
    0.41
    Throughout
    0.41
    maq
    0.40
    throughout
    0.39
    цездатний
    0.39
    ObjectContext
    0.38
     sige
    0.38
     kvalitet
    0.38
    Activations Density 0.008%

    No Known Activations