© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 695
    Prev
    Next
    INDEX
    Explanations

    LaTeX math syntax

    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
     invitado
    -0.63
    quelize
    -0.60
    ThroughAttribute
    -0.58
    lafen
    -0.57
    lccn
    -0.56
     présentés
    -0.55
    XmlAccessorType
    -0.55
     morire
    -0.55
     invitamos
    -0.54
     ricevuto
    -0.53
    POSITIVE LOGITS
    存于互联网档案馆
    0.75
     }}"></
    0.68
    ChildScrollView
    0.65
     ?></
    0.56
    </>
    0.56
    abs
    0.55
    клопе
    0.55
     Janis
    0.54
     abs
    0.54
     estekak
    0.53
    Activations Density 0.364%

    No Known Activations