© 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. 1-RES-MATRYOSHKA-DC
    7. 16
    Prev
    Next
    INDEX
    Explanations

    references to legal descriptions and obligations

    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
    𝙫
    -0.65
    enscha
    -0.64
    𝙣
    -0.63
    𝙜
    -0.63
     Osh
    -0.63
    𝙪
    -0.61
    bigoplus
    -0.60
    שְׁ
    -0.58
    ု
    -0.58
    vel
    -0.57
    POSITIVE LOGITS
    ,
    1.91
    ,<
    1.57
    ,-,
    1.50
    ，
    1.50
    °,
    1.48
    ،
    1.45
    (),
    1.44
    _,
    1.44
    .,
    1.43
    *,
    1.42
    Activations Density 6.397%

    No Known Activations