© 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. 3000
    Prev
    Next
    INDEX
    Explanations

    HTML attributes

    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
    endphp
    -0.88
    EndProject
    -0.75
    -------
    -0.66
     nahilalakip
    -0.63
    httphttps
    -0.63
     PLWABN
    -0.63
    rénées
    -0.62
     Ulf
    -0.61
    InjectMocks
    -0.60
     mergeFrom
    -0.58
    POSITIVE LOGITS
    attr
    2.58
     attr
    1.79
    Attr
    1.16
     Attr
    1.04
    ATTR
    0.91
     ATTR
    0.78
     "..\..\..\
    0.67
    Attra
    0.65
     Attraction
    0.65
    attrs
    0.63
    Activations Density 0.005%

    No Known Activations