© 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. 2-RES-MATRYOSHKA-DC
    7. 7181
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers, especially numeric patterns and derivatives

    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
     "
    -0.69
     -
    -0.63
     '
    -0.59
    <eos>
    -0.57
     \
    -0.56
    ↵↵
    -0.56
     I
    -0.53
     (
    -0.53
     «
    -0.52
     *
    -0.52
    POSITIVE LOGITS
     myſelf
    1.37
     himſelf
    1.31
     Majefty
    1.27
     Monfieur
    1.24
     itſelf
    1.23
     Theſe
    1.23
     themſelves
    1.22
     Jefus
    1.22
     Anſ
    1.20
     raiſ
    1.18
    Activations Density 1.182%

    No Known Activations