© 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. 5823
    Prev
    Next
    INDEX
    Explanations

    expressions of certainty or likelihood

    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
    どうしても
    -0.65
    ροσ
    -0.60
     perhaps
    -0.57
     вдруг
    -0.57
     lalu
    -0.56
    weilen
    -0.54
     dunque
    -0.54
    ритори
    -0.54
    Perhaps
    -0.53
     perchance
    -0.53
    POSITIVE LOGITS
     probably
    2.06
     Probably
    2.02
    Probably
    1.91
    probably
    1.89
     prolly
    1.40
     probablemente
    1.15
     probablement
    1.09
     provavelmente
    0.97
     наверное
    0.95
     pretty
    0.94
    Activations Density 0.011%

    No Known Activations