© 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. 0-RES-MATRYOSHKA-DC
    7. 11735
    Prev
    Next
    INDEX
    Explanations

    HTML link and stylesheet tags

    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
     parteci
    -0.59
    ècie
    -0.56
     juges
    -0.56
     UPON
    -0.56
     Gartner
    -0.54
     الرياضيه
    -0.54
    ometrial
    -0.53
     pylint
    -0.52
     indor
    -0.52
    itulo
    -0.51
    POSITIVE LOGITS
    ="_
    3.75
    ='_
    1.86
     ligiloj
    0.82
    SharedDtor
    0.78
    UnusedPrivate
    0.65
     jsPsych
    0.62
     protoimpl
    0.62
    Tē
    0.62
    ⓧ
    0.58
     للاسماء
    0.56
    Activations Density 0.000%

    No Known Activations