© 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. 1-RES-MATRYOSHKA-DC
    7. 610
    Prev
    Next
    INDEX
    Explanations

    references to scientific data, technical terminology, or specific detailed information

    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
     pinulongan
    -0.83
    NameInMap
    -0.71
    shub
    -0.69
    новништво
    -0.66
     AttributeSet
    -0.65
     Mockito
    -0.65
     Syrie
    -0.65
    /***/
    -0.63
     propOrder
    -0.63
     Yose
    -0.62
    POSITIVE LOGITS
    AN
    1.82
    anan
    1.59
    an
    1.55
    ans
    1.54
    ANS
    1.45
    ant
    1.41
    nan
    1.38
     AN
    1.37
    pan
    1.36
    ants
    1.35
    Activations Density 1.321%

    No Known Activations