© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1024
    Prev
    Next
    INDEX
    Explanations

    scientific research methods

    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.22.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.22.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
    PhysRevLett
    -0.71
     }}"></
    -0.64
     testGet
    -0.64
    enumi
    -0.60
    Према
    -0.59
    ivasan
    -0.58
    AccessorTable
    -0.57
     Found
    -0.57
    AsUp
    -0.56
    gham
    -0.56
    POSITIVE LOGITS
     performed
    2.28
     done
    1.97
     conducted
    1.91
     Performed
    1.87
    performed
    1.82
     undertaken
    1.63
    conducted
    1.60
    done
    1.59
    Performed
    1.59
     dilakukan
    1.58
    Activations Density 1.790%

    No Known Activations