© 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. 6-RES-MATRYOSHKA-DC
    7. 349
    Prev
    Next
    INDEX
    Explanations

    the equals sign after "ref-type"

    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
    Hozzáférés
    -0.76
     Paglinawan
    -0.72
    RegressionTest
    -0.70
    CommonModule
    -0.70
     ‘
    -0.69
    verwijspagina
    -0.69
    Personendaten
    -0.67
    Дереккөздер
    -0.66
     fieldNum
    -0.65
     “
    -0.63
    POSITIVE LOGITS
    ="
    0.94
     Audiodateien
    0.90
    multer
    0.77
    ReusableCell
    0.69
    ="_
    0.67
     végétale
    0.65
     vocale
    0.64
     Mutable
    0.63
    <%=
    0.63
    ="-
    0.60
    Activations Density 0.565%

    No Known Activations