© 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. 2-RES-MATRYOSHKA-DC
    7. 5797
    Prev
    Next
    INDEX
    Explanations

    references to specific subjects or study participants

    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
     object
    -1.47
    object
    -1.33
     Object
    -1.24
    Object
    -1.15
     objects
    -1.09
    OBJECT
    -1.06
     OBJECT
    -1.02
     Objekt
    -0.98
     obj
    -0.97
     Objects
    -0.94
    POSITIVE LOGITS
     subjects
    1.70
     Subjects
    1.63
     SUBJECTS
    1.46
    subjects
    1.41
    Subjects
    1.14
    Personendaten
    0.80
     sujets
    0.79
    IsMutable
    0.71
    InSection
    0.71
     <<<<<<<<<<<<<<
    0.68
    Activations Density 0.007%

    No Known Activations