© 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. 3-RES-MATRYOSHKA-DC
    7. 2363
    Prev
    Next
    INDEX
    Explanations

    the word "counsel", often followed by other legal terms

    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
     Board
    -0.63
    boards
    -0.59
     الحره
    -0.58
    board
    -0.57
    BOARD
    -0.57
    Board
    -0.56
     Boards
    -0.56
     tevreden
    -0.56
     nahilalakip
    -0.55
     مرئيه
    -0.54
    POSITIVE LOGITS
     counsel
    2.78
     Counsel
    2.36
    Counsel
    2.16
     COUNSEL
    2.13
     counsels
    2.08
    coun
    1.74
     coun
    1.30
    Coun
    1.16
     counseling
    1.15
     counselling
    1.13
    Activations Density 0.017%

    No Known Activations