© 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. 4218
    Prev
    Next
    INDEX
    Explanations

    references to a specific research institution or organization

    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
    ViewFeatures
    -0.71
    djangoproject
    -0.69
    بوابة
    -0.65
    '}}
    -0.65
    ━━━━━━━━
    -0.65
    SequentialGroup
    -0.64
    ConverterFactory
    -0.63
     Allociné
    -0.62
     Sop
    -0.60
     fieldNum
    -0.60
    POSITIVE LOGITS
     Sk
    3.23
    Sk
    3.17
     sk
    3.09
    sk
    2.88
     SK
    2.86
    SK
    2.67
     Skid
    1.63
     skim
    1.46
    skim
    1.44
    ssk
    1.41
    Activations Density 0.026%

    No Known Activations