© 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. 6-RES-MATRYOSHKA-DC
    7. 798
    Prev
    Next
    INDEX
    Explanations

    words related to roles of software or machines, technical job titles, and also some names.

    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
    skraft
    -0.90
    ñez
    -0.81
    quatch
    -0.76
    httphttps
    -0.75
     Benav
    -0.75
    createClass
    -0.74
    ikyuu
    -0.74
    swick
    -0.74
     peindre
    -0.70
    исленность
    -0.70
    POSITIVE LOGITS
    er
    1.87
    ER
    1.30
    ler
    1.19
    ner
    1.15
    ter
    1.13
    der
    1.13
    ider
    1.08
    rer
    1.07
    inger
    1.05
    nder
    1.04
    Activations Density 3.173%

    No Known Activations