© 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. 0-RES-MATRYOSHKA-DC
    7. 14211
    Prev
    Next
    INDEX
    Explanations

    references to the extent or degree of something, particularly emphasizing the level or amount of progress or similarity

    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
     Far
    -0.77
    much
    -0.71
    Far
    -0.66
    providedIn
    -0.65
    hdashline
    -0.64
     much
    -0.63
     THAN
    -0.61
     snippetHide
    -0.58
    führ
    -0.57
    far
    -0.57
    POSITIVE LOGITS
    lapsingToolbar
    0.71
     facie
    0.65
    WebServlet
    0.57
     bisher
    0.56
    ostante
    0.55
     combineReducers
    0.54
    AndEndTag
    0.54
    TagMode
    0.53
    mények
    0.51
     bisherigen
    0.51
    Activations Density 0.003%

    No Known Activations