© 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. 4285
    Prev
    Next
    INDEX
    Explanations

    expressions of certainty or perception

    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
     appearance
    -1.55
     appearing
    -1.47
     appeared
    -1.45
     appear
    -1.42
     appearances
    -1.38
    appeared
    -1.34
     Appear
    -1.28
    appear
    -1.27
    appearance
    -1.25
     Appearance
    -1.24
    POSITIVE LOGITS
     seems
    1.38
     seem
    1.33
     Seems
    1.31
    Seems
    1.30
     seemed
    1.28
    seems
    1.23
    seemed
    1.13
    seem
    0.97
     Seem
    0.94
     semblent
    0.91
    Activations Density 0.031%

    No Known Activations