© 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. 12-RES-MATRYOSHKA-DC
    7. 1880
    Prev
    Next
    INDEX
    Explanations

    references to small sizes or small entities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    umab
    -0.66
     Gaulle
    -0.62
    vės
    -0.60
    iasis
    -0.59
    closedir
    -0.59
    CreateMap
    -0.57
    glEnable
    -0.56
    ñata
    -0.55
    lendi
    -0.55
    bonucleic
    -0.55
    POSITIVE LOGITS
     small
    1.38
    Small
    1.38
     SMALL
    1.37
    small
    1.33
     Small
    1.32
     tiny
    1.32
    SMALL
    1.23
     (<
    1.13
    tiny
    1.11
    Tiny
    1.09
    Activations Density 1.985%

    No Known Activations