© 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. 239
    Prev
    Next
    INDEX
    Explanations

    words related to manufacturing, babies, teeth, and motorcycles

    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
    +#+#
    -0.95
    extAlignment
    -0.81
    Geplaatst
    -0.78
    WriteBarrier
    -0.73
    دانشنامهٔ
    -0.70
    interopRequire
    -0.68
    ScopeManager
    -0.67
    исленность
    -0.66
     kasarigan
    -0.66
    Хьажоргаш
    -0.66
    POSITIVE LOGITS
     contigo
    0.63
     comigo
    0.57
     céré
    0.54
     stessa
    0.53
    futbolista
    0.51
     createSlice
    0.50
    胚
    0.50
    AppCompat
    0.49
     stessi
    0.49
    ѓ
    0.48
    Activations Density 9.311%

    No Known Activations