© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 305
    Prev
    Next
    INDEX
    Explanations

    the letter 'j' or the term 'userRole' followed by some term

    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
     możliwe
    -0.66
    setAll
    -0.56
    ėl
    -0.53
    govor
    -0.52
    And
    -0.50
     Easton
    -0.50
    ربعة
    -0.50
     Toten
    -0.49
    The
    -0.48
     måte
    -0.47
    POSITIVE LOGITS
     j
    1.75
     J
    1.73
    J
    1.51
     JJ
    1.46
    j
    1.46
     JPM
    1.38
    JJ
    1.34
     jc
    1.34
     Jamb
    1.31
     jj
    1.30
    Activations Density 2.878%

    No Known Activations