© 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. 3-RES-MATRYOSHKA-DC
    7. 1693
    Prev
    Next
    INDEX
    Explanations

    citations with bracketed numbers

    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
     Trem
    -0.60
    
    -0.59
    ETER
    -0.56
    rungsseite
    -0.56
    onomi
    -0.56
    Trem
    -0.55
    пра
    -0.54
     indisponible
    -0.54
     actionTypes
    -0.54
     #
    -0.53
    POSITIVE LOGITS
    ]{
    2.34
    ]{\
    1.17
    }]{
    1.10
    principalTable
    1.07
    )]{
    0.91
    SequentialGroup
    0.87
    reszcie
    0.79
     hâte
    0.76
     itſelf
    0.74
    stęp
    0.73
    Activations Density 0.063%

    No Known Activations