© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 545
    Prev
    Next
    INDEX
    Explanations

    nouns of different types, seemingly without any unifying pattern

    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
     beginnetje
    -0.74
     հղումներ
    -0.73
     мәкал
    -0.73
    fastjson
    -0.71
     externi
    -0.70
    yntaxException
    -0.70
    Morfologia
    -0.69
    Cyfeiriadau
    -0.67
    LookAnd
    -0.66
     كومونز
    -0.63
    POSITIVE LOGITS
    writeObject
    0.61
    AutoresizingMask
    0.58
    حوالہ
    0.57
    ftance
    0.56
    rachtet
    0.56
     _)
    0.56
    neſs
    0.54
    cyjna
    0.53
    μως
    0.52
    তথ্যসূত্র
    0.52
    Activations Density 7.234%

    No Known Activations