© 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. 6-RES-MATRYOSHKA-DC
    7. 162
    Prev
    Next
    INDEX
    Explanations

    articles ("the", "a") and prepositions ("by", "in", "of", "for", etc.) surrounding words indicating a comparison or mathematical statement.

    oai_token-act-pair · gemini-2.0-flash
    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
    [++
    -0.54
    jsonwebtoken
    -0.51
     también
    -0.50
    badlogic
    -0.49
    ।
    -0.48
     téléphonique
    -0.47
     descubrimiento
    -0.47
     serves
    -0.47
    ikti
    -0.47
    also
    -0.46
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.84
     utafitiHapana
    0.78
    ostante
    0.72
    Whilst
    0.70
     Within
    0.68
    ScopeManager
    0.68
    InputBorder
    0.67
     للاسماء
    0.67
     Whilst
    0.66
    InSection
    0.66
    Activations Density 3.188%

    No Known Activations