© 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. 2-RES-MATRYOSHKA-DC
    7. 6435
    Prev
    Next
    INDEX
    Explanations

    references to the quality of production or filming

    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
     Dore
    -0.63
     Brun
    -0.57
    LayoutStyle
    -0.57
     Katz
    -0.57
    toPromise
    -0.57
    Brun
    -0.56
    Ol
    -0.54
    Dore
    -0.54
     Schulze
    -0.53
    택
    -0.53
    POSITIVE LOGITS
     tight
    3.83
     Tight
    3.59
    Tight
    3.47
    tight
    3.41
     tighter
    3.02
     tightness
    2.77
     tighten
    2.61
     tightly
    2.59
     tightened
    2.52
     tightening
    2.47
    Activations Density 0.007%

    No Known Activations