© 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. 1-RES-MATRYOSHKA-DC
    7. 386
    Prev
    Next
    INDEX
    Explanations

    sentences consisting mainly of punctuation marks

    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
     ripar
    -0.55
    Ữ
    -0.55
    legungen
    -0.51
    agré
    -0.49
    Mantenimiento
    -0.49
     omge
    -0.48
    ม้
    -0.48
    itectura
    -0.47
     ponts
    -0.46
    hau
    -0.45
    POSITIVE LOGITS
    GraphicsUnit
    0.90
     يتيمه
    0.82
    󠁿
    0.77
    存于互联网档案馆
    0.74
    EDEFAULT
    0.73
    kmäler
    0.73
     NSCoder
    0.71
     ModelExpression
    0.70
    LabelTagHelper
    0.69
     referenties
    0.68
    Activations Density 1.430%

    No Known Activations