© 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. 0-RES-MATRYOSHKA-DC
    7. 11096
    Prev
    Next
    INDEX
    Explanations

    references to prior art or existing methods

    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
     Arts
    -1.26
     Artist
    -1.24
    Arts
    -1.14
     Arti
    -1.13
    ART
    -1.11
     ARTIST
    -1.11
    Artist
    -1.09
     Artists
    -1.09
    arts
    -1.05
     ARTS
    -1.02
    POSITIVE LOGITS
     art
    0.73
     liggen
    0.53
    subplots
    0.51
    köz
    0.51
    ontale
    0.49
    getNome
    0.49
    elho
    0.48
    StoryboardSegue
    0.48
    nourriture
    0.48
     Syrie
    0.47
    Activations Density 0.008%

    No Known Activations