© 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. 4148
    Prev
    Next
    INDEX
    Explanations

    references to specific sections within a document

    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
     part
    -0.66
     parts
    -0.57
    part
    -0.54
    parts
    -0.53
     части
    -0.47
    i
    -0.47
     części
    -0.45
     Teil
    -0.43
    c
    -0.43
    Parts
    -0.42
    POSITIVE LOGITS
     Section
    1.21
    providedIn
    1.03
    Section
    0.96
    Personensuche
    0.92
     Walkover
    0.90
    LayoutStyle
    0.89
     saites
    0.89
     defaultstate
    0.88
     ProtoMessage
    0.87
    AndEndTag
    0.87
    Activations Density 0.040%

    No Known Activations