© 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. 11314
    Prev
    Next
    INDEX
    Explanations

    claims or assertions that are marked as allegedly true or unverified

    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
    tonode
    -0.71
    новниш
    -0.67
     disponibilités
    -0.64
    /**
    -0.64
     bezeichneter
    -0.63
    ัณฑ
    -0.60
    meneu
    -0.60
    GHIJKLM
    -0.60
    deviantart
    -0.60
    ✨:
    -0.59
    POSITIVE LOGITS
     purported
    2.73
     purport
    2.31
     ostensibly
    1.33
     supposedly
    1.30
     supuestamente
    0.98
     allegedly
    0.95
     pur
    0.85
     reportedly
    0.81
     osten
    0.80
     prétend
    0.68
    Activations Density 0.002%

    No Known Activations