© 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
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 4124
    Prev
    Next
    INDEX
    Explanations

    patterns involving complex mathematical expressions, often related to scientific calculations or formulae

    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
    ISupport
    -0.79
    PerformLayout
    -0.67
    GraphicsUnit
    -0.63
    addCriterion
    -0.61
     vanske
    -0.60
     innehå
    -0.55
     Référence
    -0.54
     EnglishChoose
    -0.54
    tanleria
    -0.53
    oredCriteria
    -0.53
    POSITIVE LOGITS
    ChildScrollView
    0.65
    曖昧さ回避
    0.65
     виправивши
    0.64
    stackoverflow
    0.64
    }{*}{}
    0.57
    brochen
    0.57
    </thead>
    0.55
     TestBed
    0.55
     {}));
    0.55
     })}
    0.54
    Activations Density 2.617%

    No Known Activations