© 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. 4043
    Prev
    Next
    INDEX
    Explanations

    sentences expressing opinions or evaluations

    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
     للمعارف
    -0.85
    <bos>
    -0.75
    WillAppear
    -0.72
    iosync
    -0.71
    KommentareTeilen
    -0.67
     don
    -0.64
    Màu
    -0.64
    CodeAttribute
    -0.63
    Kích
    -0.63
    publique
    -0.60
    POSITIVE LOGITS
     combineReducers
    0.60
     doInBackground
    0.53
    DTD
    0.52
    يكب
    0.50
     raste
    0.50
     betweenstory
    0.48
     &___
    0.48
    8
    0.47
    Solución
    0.47
     følgende
    0.47
    Activations Density 0.653%

    No Known Activations