© 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. 4240
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions containing nested parentheses and specific operators

    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
     MenuView
    -0.73
    ModelAdmin
    -0.71
     InputDecoration
    -0.65
    KommentareTeilen
    -0.65
    enderror
    -0.65
    itemView
    -0.64
    Autoritní
    -0.64
    Portail
    -0.63
    </tfoot>
    -0.62
    AddTagHelper
    -0.62
    POSITIVE LOGITS
    ((
    2.08
     ((
    2.05
    (((
    1.90
     (((
    1.75
    ((((
    1.66
    )((
    1.63
    ((-
    1.60
    =((
    1.43
     ((((
    1.41
    >((
    1.34
    Activations Density 0.036%

    No Known Activations