Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14643
    Prev
    Next
    INDEX
    Explanations

    code snippets or formatting cues related to indentation or line breaks

    oai_token-act-pair · gpt-4.1-nano
    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
     Bra
    -0.63
    Bra
    -0.57
     http
    -0.55
    http
    -0.54
     pinulongan
    -0.54
    y
    -0.54
    2
    -0.54
    `
    -0.52
     Bro
    -0.52
    1
    -0.52
    POSITIVE LOGITS
    br
    1.03
    CloseOperation
    0.91
    ConstraintMaker
    0.88
     br
    0.79
    :✨
    0.78
     '\\;'
    0.78
    NUMX
    0.71
     Gregorian
    0.71
     öffnungszeiten
    0.70
    ^(@)
    0.70
    Activations Density 0.001%

    No Known Activations