© 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. 4176
    Prev
    Next
    INDEX
    Explanations

    mentions of obtaining or providing informed consent

    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
     worshi
    -0.57
    alquiler
    -0.55
     kasarigan
    -0.54
    illus
    -0.53
     Ressources
    -0.52
     story
    -0.51
    mtable
    -0.50
    äť
    -0.49
     McCra
    -0.49
    gie
    -0.48
    POSITIVE LOGITS
     informed
    3.09
     Informed
    2.91
    Informed
    2.73
    informed
    2.66
     inform
    2.30
     informs
    2.23
     INFORM
    2.09
     informing
    2.02
     Inform
    1.99
    Inform
    1.98
    Activations Density 0.045%

    No Known Activations