© 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. 737
    Prev
    Next
    INDEX
    Explanations

    ambiguous or uncertain status indicators, often relating to conditions or situations that are yet to be resolved or determined

    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
     الاطلاع
    -0.83
    ConstraintMaker
    -0.69
    lgari
    -0.66
     препратки
    -0.57
    ranean
    -0.57
     виправивши
    -0.57
    tometer
    -0.53
    ANDUM
    -0.52
    awancara
    -0.52
    skraft
    -0.51
    POSITIVE LOGITS
    saraba
    0.68
    XmlRootElement
    0.67
     utafitiHapana
    0.65
    OrNil
    0.65
    ="@+
    0.64
    WebServlet
    0.61
    issão
    0.59
     ویکی‌پدی
    0.56
    rboles
    0.56
     perpétu
    0.56
    Activations Density 4.158%

    No Known Activations