© 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. 3-RES-MATRYOSHKA-DC
    7. 735
    Prev
    Next
    INDEX
    Explanations

    instances of "cap" followed by other characters, potentially within citation markers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Referències
    -0.73
     Ramona
    -0.60
    Igles
    -0.57
     מוכ
    -0.57
     Iglesias
    -0.56
    RTEX
    -0.56
    спонд
    -0.55
     Aviv
    -0.54
     Prato
    -0.54
    //}
    -0.53
    POSITIVE LOGITS
    cap
    3.42
     cap
    3.36
    Cap
    3.28
     Cap
    3.25
     caps
    2.91
     Caps
    2.70
    CAP
    2.69
     CAP
    2.67
    caps
    2.67
    Caps
    2.39
    Activations Density 0.424%

    No Known Activations