© 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. 1118
    Prev
    Next
    INDEX
    Explanations

    the word "position" and related terms such as "location" and "orientation".

    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
     henvisninger
    -0.90
    bewerken
    -0.86
     Paglinawan
    -0.79
     autorytatywna
    -0.77
    Durata
    -0.74
    roduction
    -0.73
    migrationBuilder
    -0.72
     gustó
    -0.71
    addCriterion
    -0.71
     CWE
    -0.70
    POSITIVE LOGITS
     position
    2.13
     positions
    2.02
     Position
    1.94
    position
    1.91
     POSITION
    1.88
    Position
    1.77
     Positions
    1.77
     positioned
    1.75
     positioning
    1.69
    POSITION
    1.59
    Activations Density 0.806%

    No Known Activations