© 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. 3-RES-MATRYOSHKA-DC
    7. 2861
    Prev
    Next
    INDEX
    Explanations

    the numbers two and three, and sometimes numbers close to them

    oai_token-act-pair · gemini-2.0-flash
    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
    Viel
    -0.67
     ModelExpression
    -0.57
     صوتيه
    -0.57
     Più
    -0.55
    ėjas
    -0.55
    duma
    -0.54
    ocellular
    -0.52
     geldig
    -0.51
    Whip
    -0.51
     parcour
    -0.51
    POSITIVE LOGITS
    WebServlet
    0.71
    <bos>
    0.65
     disambiguazione
    0.63
    AndroidJUnit
    0.61
    %)$
    0.61
    verwijspagina
    0.60
     Савезне
    0.58
    webElementXpaths
    0.57
    -------
    0.57
    かわらず
    0.57
    Activations Density 0.189%

    No Known Activations