© 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. 3781
    Prev
    Next
    INDEX
    Explanations

    neural responses to specific sensory stimuli

    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
    RegisterType
    -0.67
    HomeAsUpEnabled
    -0.61
    annin
    -0.59
    बस
    -0.57
    enterOuterAlt
    -0.56
    íncia
    -0.54
     Seni
    -0.54
    enumi
    -0.53
     بوی
    -0.53
     affari
    -0.53
    POSITIVE LOGITS
     stimulus
    2.34
     Stimulus
    2.06
    stimulus
    1.91
     stimuli
    1.87
    Stim
    1.05
     estí
    1.04
     estímulo
    1.01
     Stim
    0.76
    刺激
    0.72
    afficheront
    0.71
    Activations Density 0.003%

    No Known Activations