© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-RES-MATRYOSHKA-DC
    7. 29713
    Prev
    Next
    INDEX
    Explanations

    words related to making assumptions or speculating

    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
     المعيارى
    -0.68
    WriteLiteral
    -0.67
     חיצוניים
    -0.61
    บัติ
    -0.60
     nakalista
    -0.60
    Cus
    -0.59
     Qua
    -0.58
     ESE
    -0.58
     Cassini
    -0.57
     Arki
    -0.57
    POSITIVE LOGITS
    jecture
    1.46
     conjecture
    1.23
     conjectures
    0.98
    jectures
    0.96
     conject
    0.85
     cser
    0.72
     Pollock
    0.67
    Penulis
    0.65
     préféré
    0.62
    IntoConstraints
    0.62
    Activations Density 0.002%

    No Known Activations