© 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. 7249
    Prev
    Next
    INDEX
    Explanations

    sentences that consist solely of a period

    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
    msgid
    -2.06
    DockStyle
    -0.93
     doInBackground
    -0.86
     AttributeSet
    -0.86
     оригіналу
    -0.85
    ConstraintMaker
    -0.84
    InputTagHelper
    -0.75
     onBind
    -0.74
    riwal
    -0.71
    laubnis
    -0.69
    POSITIVE LOGITS
    msgstr
    3.50
     Stacey
    0.53
    str
    0.51
    toEqual
    0.51
    tation
    0.51
     mist
    0.50
    stro
    0.50
    跟著
    0.48
     traseiro
    0.47
     Monroe
    0.46
    Activations Density 0.000%

    No Known Activations