© 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. 932
    Prev
    Next
    INDEX
    Explanations

    segments indicating a section or portion of a text

    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
     components
    -1.41
     Components
    -1.36
     elements
    -1.33
     portions
    -1.30
    components
    -1.25
     sections
    -1.25
     Elements
    -1.20
     pieces
    -1.20
    Components
    -1.18
     ELEMENTS
    -1.17
    POSITIVE LOGITS
     part
    2.59
    part
    2.22
    Part
    2.20
     Part
    2.14
     PART
    1.59
    PART
    1.35
     parte
    1.16
     onderdeel
    1.08
     Teil
    1.07
     часть
    1.02
    Activations Density 0.057%

    No Known Activations