© 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. 3-RES-MATRYOSHKA-DC
    4. 92
    Prev
    Next
    INDEX
    Explanations

    scientific results including numbers, standard deviations, units, and sometimes variable names

    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
    |}{}
    -0.60
    Посилання
    -0.53
    ])]
    -0.52
     nepri
    -0.50
    ]])
    -0.50
    }}}\
    -0.50
    "]))
    -0.50
     much
    -0.49
    ]))
    -0.49
    )])
    -0.48
    POSITIVE LOGITS
     ExecuteAsync
    1.08
    IntoConstraints
    1.07
    TagMode
    1.06
    AddTagHelper
    0.94
    MessageOf
    0.93
     continúas
    0.89
    зулта
    0.87
     propOrder
    0.83
    HtmlAttribute
    0.79
    featureID
    0.78
    Activations Density 11.103%

    No Known Activations