© 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. 3408
    Prev
    Next
    INDEX
    Explanations

    references to code-related concepts, such as programming, segments, and offsets

    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
     hvem
    -0.61
    FailureListener
    -0.61
    )(((
    -0.60
     vapore
    -0.59
     terça
    -0.57
    ([^
    -0.57
     samarbeid
    -0.56
    (!__
    -0.56
    RatingBar
    -0.56
    kru
    -0.56
    POSITIVE LOGITS
     offset
    3.09
     Offset
    2.89
    offset
    2.80
    Offset
    2.66
     offsets
    2.50
     OFFSET
    2.22
    OFFSET
    2.08
    offsets
    1.70
    Offsets
    1.58
    偏移
    1.46
    Activations Density 0.016%

    No Known Activations