© 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. 0-RES-MATRYOSHKA-DC
    7. 14286
    Prev
    Next
    INDEX
    Explanations

    the probability of selecting specific combinations of letters in a sampling process

    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
     letter
    -1.75
    letter
    -1.64
    Letter
    -1.60
     Letter
    -1.53
     LETTER
    -1.52
    LETTER
    -1.37
     lettre
    -0.96
    出版年
    -0.93
     lettera
    -0.87
     للاسماء
    -0.86
    POSITIVE LOGITS
     letters
    0.84
     destaque
    0.57
     letras
    0.56
    TagHelpers
    0.56
     lettres
    0.53
     Letters
    0.52
     起
    0.48
    ziehung
    0.45
     mundos
    0.45
    Letters
    0.44
    Activations Density 0.007%

    No Known Activations