© 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. 6808
    Prev
    Next
    INDEX
    Explanations

    references to specific appearances or instances of visual or conceptual presentation

    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
     seem
    -1.38
     seems
    -1.36
     Seems
    -1.27
    Seems
    -1.23
     seemed
    -1.21
    seems
    -1.13
    seem
    -1.06
     Seem
    -1.01
    seemed
    -1.00
     semblent
    -0.93
    POSITIVE LOGITS
     appearance
    2.78
     Appearance
    2.47
    appearance
    2.41
     appearances
    2.36
    Appearance
    2.03
     Appearances
    1.98
     appearing
    1.91
     appeared
    1.78
    Appearances
    1.75
    appeared
    1.70
    Activations Density 0.076%

    No Known Activations