© 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. 1-RES-MATRYOSHKA-DC
    7. 35
    Prev
    Next
    INDEX
    Explanations

    references to specific "this" or "these," indicating focus on particular items or concepts being discussed

    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
    LookAnd
    -0.59
    äki
    -0.59
    ául
    -0.58
     Agamemnon
    -0.58
     Esau
    -0.58
     Dubuque
    -0.57
    enderror
    -0.57
     Ae
    -0.56
    odine
    -0.56
    ResponseDto
    -0.56
    POSITIVE LOGITS
     this
    3.72
    this
    3.06
     THIS
    2.75
     This
    2.63
    This
    2.56
    THIS
    2.44
     these
    2.20
     questo
    2.20
     questa
    2.19
     dieses
    2.11
    Activations Density 2.977%

    No Known Activations