© 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. 1-RES-MATRYOSHKA-DC
    7. 526
    Prev
    Next
    INDEX
    Explanations

    the sequence of the letter "m" repeated multiple times

    oai_token-act-pair · gpt-4.1-nano
    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
     M
    -1.19
     getM
    -1.05
    M
    -1.04
    MM
    -1.01
     М
    -0.91
     MM
    -0.90
    AM
    -0.85
    getM
    -0.85
    pM
    -0.84
    iM
    -0.82
    POSITIVE LOGITS
    m
    1.77
     m
    0.74
    +#+#
    0.65
    abestanden
    0.60
     metres
    0.58
    matchCondition
    0.57
    offsetof
    0.56
     metre
    0.56
    mC
    0.55
    NameInMap
    0.54
    Activations Density 0.141%

    No Known Activations