© 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. 3799
    Prev
    Next
    INDEX
    Explanations

    references to near completeness or almost certainty

    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
    ifoli
    -0.70
     getItemCount
    -0.68
    ceutical
    -0.65
    owol
    -0.65
     Amad
    -0.62
    gerald
    -0.60
    Wohn
    -0.59
     discorso
    -0.58
    Verkehr
    -0.58
    ség
    -0.58
    POSITIVE LOGITS
    nearly
    2.23
     Nearly
    2.19
     nearly
    2.17
    Nearly
    2.06
     NEAR
    1.00
     Approximately
    0.87
    Approximately
    0.82
     près
    0.81
     approximately
    0.78
     roughly
    0.77
    Activations Density 0.005%

    No Known Activations