© 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. 4079
    Prev
    Next
    INDEX
    Explanations

    references to a specific bed, often with numbered or possessive context

    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
    HasForeignKey
    -0.77
    GOTREF
    -0.76
    matchCondition
    -0.72
     חיצוניים
    -0.69
    іга
    -0.67
    amazonaws
    -0.66
     cire
    -0.66
    ProcessEvent
    -0.65
    Izvori
    -0.64
    millimeters
    -0.63
    POSITIVE LOGITS
     bed
    4.22
    bed
    3.58
     Bed
    3.56
    Bed
    3.52
     beds
    3.48
     BED
    3.31
     Beds
    3.13
    beds
    3.11
    BED
    2.92
    Beds
    2.63
    Activations Density 0.021%

    No Known Activations