© 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. 299
    Prev
    Next
    INDEX
    Explanations

    references to the presence or occurrence of specific items or features

    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
     NSCoder
    -0.69
     noqa
    -0.67
    évaluateur
    -0.67
     ComVisible
    -0.65
     WaitForSeconds
    -0.65
     betweenstory
    -0.65
    AppMethodBeat
    -0.65
    +#+#
    -0.65
     accedi
    -0.65
    曖昧さ回避
    -0.65
    POSITIVE LOGITS
     present
    4.88
    present
    4.38
     Present
    4.38
    Present
    4.28
     PRESENT
    4.03
     présent
    3.36
    PRESENT
    3.31
     presente
    3.13
     presentes
    2.92
     présente
    2.91
    Activations Density 0.509%

    No Known Activations