© 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. 11685
    Prev
    Next
    INDEX
    Explanations

    references to the purpose of performing certain actions or tasks

    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
    enumi
    -0.54
     Vor
    -0.53
    Vor
    -0.52
    hver
    -0.52
    IsContent
    -0.51
    vor
    -0.50
    lieg
    -0.50
     před
    -0.49
    pred
    -0.49
    Pred
    -0.48
    POSITIVE LOGITS
     pour
    1.73
    pour
    1.39
     Pour
    1.31
    Pour
    1.30
     POUR
    1.06
     pours
    0.86
    POUR
    0.74
    ніципалі
    0.66
     forState
    0.62
     pouring
    0.60
    Activations Density 0.003%

    No Known Activations