© 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. 24-RES-MATRYOSHKA-DC
    7. 426
    Prev
    Next
    INDEX
    Explanations

    text from scientific research papers about testing on mice

    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/blocks.24.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Phari
    -0.55
    Lugares
    -0.54
     memer
    -0.50
    VIAF
    -0.50
     chi̍t
    -0.48
     '</
    -0.47
     Masyarakat
    -0.46
     EconPapers
    -0.46
     съм
    -0.46
    phem
    -0.45
    POSITIVE LOGITS
     mice
    1.30
     Mice
    1.05
     animals
    1.05
    Mice
    1.00
     rats
    0.98
    mice
    0.96
     Animals
    0.95
     rodents
    0.87
    Animals
    0.85
     mouse
    0.84
    Activations Density 2.155%

    No Known Activations