© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7417
    Prev
    Next
    INDEX
    Explanations

    references to the probability or likelihood of selecting a certain number of letters

    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
     char
    -0.79
     character
    -0.66
     CHARACTER
    -0.63
    fjspx
    -0.62
    Character
    -0.60
     Character
    -0.59
    jMenuItem
    -0.59
    tagPool
    -0.59
     CHAR
    -0.58
    char
    -0.57
    POSITIVE LOGITS
     letters
    3.45
     letter
    3.20
     Letters
    3.08
    letters
    3.00
    letter
    2.95
     Letter
    2.89
     LETTERS
    2.86
    Letter
    2.84
    Letters
    2.81
     LETTER
    2.77
    Activations Density 0.049%

    No Known Activations