© 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. 142
    Prev
    Next
    INDEX
    Explanations

    the letter "q", sometimes along with the word "th", and sometimes within parentheses

    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
     bor
    -0.56
     Bor
    -0.54
    istic
    -0.54
     lama
    -0.54
     OD
    -0.53
     
    -0.53
    Bor
    -0.52
     I
    -0.52
    院長
    -0.51
     BM
    -0.51
    POSITIVE LOGITS
    q
    1.98
     q
    1.98
     Q
    1.93
    Q
    1.85
     CQ
    1.52
    qtype
    1.52
     dq
    1.50
     QS
    1.48
     Quar
    1.45
     Quincy
    1.45
    Activations Density 2.350%

    No Known Activations