© 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. 3-RES-MATRYOSHKA-DC
    7. 1903
    Prev
    Next
    INDEX
    Explanations

    file names for minified javascript files

    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
     annuel
    -0.86
     anuales
    -0.77
    styleUrls
    -0.71
     utafitiHapana
    -0.68
     Vikipedi
    -0.66
    DrawerToggle
    -0.65
    حوالہ
    -0.64
     termica
    -0.63
    Referències
    -0.63
    Smack
    -0.63
    POSITIVE LOGITS
     min
    2.66
     Min
    2.52
    min
    2.50
    Min
    2.42
    MIN
    2.19
     MIN
    2.17
     mins
    1.81
     getMin
    1.77
     minu
    1.70
    getMin
    1.68
    Activations Density 0.288%

    No Known Activations