© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2595
    Prev
    Next
    INDEX
    Explanations

    references to directional movements, specifically upward and downward directions

    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
    Negative Logits
    FormTagHelper
    -0.85
    KURZBESCHREIBUNG
    -0.71
     resourceCulture
    -0.66
    })));
    -0.66
     mergeFrom
    -0.66
    RenderAtEndOf
    -0.65
    eqref
    -0.63
    WebControls
    -0.63
    }:${
    -0.63
    Vorlage
    -0.62
    POSITIVE LOGITS
    ward
    2.80
    WARD
    2.48
    wards
    2.42
     ward
    2.25
     upward
    2.22
     wards
    2.19
     downward
    2.16
     backward
    2.06
     outward
    2.02
     Backward
    1.95
    Activations Density 0.025%

    No Known Activations