© 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. 0-RES-MATRYOSHKA-DC
    7. 11532
    Prev
    Next
    INDEX
    Explanations

    concepts related to attribute identification and the presence of specific attribute labels in text

    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
    attributes
    -1.33
    Attributes
    -1.10
     utafitiHapana
    -0.84
     للمعارف
    -0.73
    AnchorStyles
    -0.57
    StructEnd
    -0.57
    ATTRIBUTES
    -0.55
     مرئيه
    -0.53
    errHandler
    -0.52
     détour
    -0.52
    POSITIVE LOGITS
     attribute
    1.89
     Attribute
    0.88
     ascribe
    0.86
     atributo
    0.85
     attribution
    0.79
     attributed
    0.79
     Attribution
    0.67
    .*")]
    0.66
     attribu
    0.64
    مصادر
    0.63
    Activations Density 0.003%

    No Known Activations