© 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. 629
    Prev
    Next
    INDEX
    Explanations

    the word "times" and numbers or words indicating multiples like "fold", "faster", and "higher"

    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
    pannt
    -0.66
    kraut
    -0.63
    MigrationBuilder
    -0.63
     pocos
    -0.61
     Bär
    -0.59
    abetta
    -0.58
    argout
    -0.58
    HomeAsUpEnabled
    -0.58
    ukah
    -0.57
     survie
    -0.57
    POSITIVE LOGITS
     times
    1.71
    Twice
    1.58
    twice
    1.55
    times
    1.52
     twice
    1.49
    Times
    1.49
     TIMES
    1.46
     Times
    1.44
     thrice
    1.42
     Twice
    1.40
    Activations Density 0.498%

    No Known Activations