© 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. 3-RES-MATRYOSHKA-DC
    7. 3082
    Prev
    Next
    INDEX
    Explanations

    the word "to", sometimes followed by "the"

    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
     purpoſe
    -0.79
     Anſ
    -0.77
     anſ
    -0.75
     myſelf
    -0.74
    InitVars
    -0.73
     preſent
    -0.73
     reaſon
    -0.73
     reafon
    -0.73
     Chriftian
    -0.73
     theſe
    -0.71
    POSITIVE LOGITS
    rän
    0.55
     Shapiro
    0.53
    ortunadamente
    0.53
    libft
    0.52
    ‚¬
    0.52
    共に
    0.51
    PyTuple
    0.49
     te
    0.48
    liothèque
    0.47
     stol
    0.47
    Activations Density 0.186%

    No Known Activations