© 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. 615
    Prev
    Next
    INDEX
    Explanations

    the word "space" plus some surrounding context

    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
    @[+][
    -0.91
     للاسماء
    -0.86
     htons
    -0.83
     Ballad
    -0.82
     hydrauli
    -0.81
     Osorio
    -0.79
     Monfieur
    -0.78
     elems
    -0.78
     OnInit
    -0.77
     Majefty
    -0.77
    POSITIVE LOGITS
     space
    2.33
     Space
    2.23
     SPACE
    2.23
     spaces
    2.20
     Spaces
    2.13
    space
    2.11
    Space
    2.11
    SPACE
    2.06
    Spaces
    2.05
    spaces
    1.99
    Activations Density 0.653%

    No Known Activations