© 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. 2470
    Prev
    Next
    INDEX
    Explanations

    references to the opening of a film event or screening

    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
     close
    -0.69
     open
    -0.68
    open
    -0.65
     Close
    -0.57
    close
    -0.55
    Open
    -0.52
     Open
    -0.52
    semantics
    -0.52
    مر
    -0.49
    Close
    -0.49
    POSITIVE LOGITS
     opening
    3.16
    Opening
    3.02
     Opening
    2.95
    opening
    2.84
     OPENING
    2.78
    OPENING
    2.53
     openings
    2.17
     opener
    1.92
     openers
    1.89
     apertura
    1.82
    Activations Density 0.060%

    No Known Activations