© 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. 6-RES-MATRYOSHKA-DC
    7. 556
    Prev
    Next
    INDEX
    Explanations

    the word "still" alone or with a comma

    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
    CrossRef
    -0.78
    PerformLayout
    -0.75
    Brainz
    -0.73
    qxd
    -0.73
    cestershire
    -0.69
    ?')
    -0.69
    Życiorys
    -0.69
    epiece
    -0.69
     mantenerse
    -0.68
     väh
    -0.68
    POSITIVE LOGITS
     still
    1.72
    still
    1.71
     Still
    1.68
    Still
    1.67
     STILL
    1.56
    STILL
    1.56
    avía
    1.13
    stil
    1.13
     todavía
    1.11
     Ainda
    1.09
    Activations Density 0.269%

    No Known Activations