© 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. 1031
    Prev
    Next
    INDEX
    Explanations

    the word "map" regardless of capitalization and its nearby tokens

    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
    providedIn
    -0.93
    ThroughAttribute
    -0.82
    HasAnnotation
    -0.81
    enderror
    -0.79
     ctypes
    -0.74
     Jefus
    -0.72
    IBarButtonItem
    -0.72
    ContentAsync
    -0.68
    GenerationType
    -0.68
    jspb
    -0.68
    POSITIVE LOGITS
     map
    1.86
     maps
    1.86
     Map
    1.66
     Maps
    1.59
    Map
    1.46
    map
    1.45
     mapping
    1.41
     mapa
    1.41
    maps
    1.38
    Maps
    1.33
    Activations Density 0.705%

    No Known Activations