© 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. 2446
    Prev
    Next
    INDEX
    Explanations

    representations of dashed lines, indicating an emphasis on the presence or significance of dashed line features

    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
     defaultstate
    -1.01
    ########.
    -0.98
     disambiguazione
    -0.97
    ChildScrollView
    -0.91
    NewUrlParser
    -0.89
    ThroughAttribute
    -0.88
    بوابة
    -0.84
     continúas
    -0.83
    tvguidetime
    -0.83
     propOrder
    -0.82
    POSITIVE LOGITS
     dashed
    2.48
    dashed
    2.31
     dash
    2.28
    dash
    2.17
    Dash
    2.06
     Dash
    2.05
     dashes
    1.83
     DASH
    1.69
     Das
    1.67
    DASH
    1.65
    Activations Density 0.021%

    No Known Activations