© 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. 208
    Prev
    Next
    INDEX
    Explanations

    references to specific labeled samples or identifiers

    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
     nahilalakip
    -0.72
     viewDidLoad
    -0.63
    SPATH
    -0.62
    erráneo
    -0.59
    HandlerContext
    -0.58
    pruchs
    -0.57
     Caz
    -0.57
    dö
    -0.57
     pourtant
    -0.57
    uttavia
    -0.57
    POSITIVE LOGITS
    pone
    4.47
    PONE
    2.25
     pone
    1.78
    pon
    1.55
    poner
    1.23
    PON
    1.13
     pon
    1.04
     PON
    0.99
     Pon
    0.98
    Pon
    0.98
    Activations Density 0.065%

    No Known Activations