© 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. 2-RES-MATRYOSHKA-DC
    7. 3728
    Prev
    Next
    INDEX
    Explanations

    mentions of legal proceedings, legal powers, or related terminology

    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
    McL
    -0.48
    NamedQueries
    -0.47
     linkovi
    -0.45
     EClass
    -0.45
     تانيه
    -0.44
    NORE
    -0.42
     InputDecoration
    -0.42
     humanas
    -0.42
     Сла
    -0.42
     interviewing
    -0.41
    POSITIVE LOGITS
     L
    0.73
     فريبيس
    0.71
     ffilm
    0.69
    SourceChecksum
    0.66
    يميديا
    0.63
    MemoryWarning
    0.61
     كومونز
    0.60
    帖最后由
    0.60
    endphp
    0.59
    ſelf
    0.59
    Activations Density 0.022%

    No Known Activations