© 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. 6894
    Prev
    Next
    INDEX
    Explanations

    expressions of certainty or emphasis denoting something as obviously true

    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
    clear
    -1.00
     clear
    -0.92
     Clear
    -0.88
    Clear
    -0.85
     clearing
    -0.75
     cleared
    -0.74
     clears
    -0.73
    Clearing
    -0.69
    clearing
    -0.68
    CLEAR
    -0.67
    POSITIVE LOGITS
     clearly
    2.53
    clearly
    2.41
     Clearly
    2.30
    Clearly
    2.20
     claramente
    1.97
     chiaramente
    1.83
     clairement
    1.59
     plainly
    1.48
     obviously
    1.21
     явно
    1.20
    Activations Density 0.020%

    No Known Activations