© 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. 2596
    Prev
    Next
    INDEX
    Explanations

    navigation-related terms or links in structured text or code

    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
    брь
    -0.54
     corrosion
    -0.50
    apunov
    -0.50
    nessione
    -0.46
    stretchr
    -0.46
    uasaan
    -0.45
    stret
    -0.44
    Lähteet
    -0.44
    {}{}
    -0.44
    coste
    -0.42
    POSITIVE LOGITS
    Portail
    0.80
    navBar
    0.65
    出版年
    0.61
    
    0.61
    findpost
    0.60
     imageNamed
    0.57
    EndProject
    0.57
    RenderAtEndOf
    0.54
    >';
    0.54
    nskap
    0.54
    Activations Density 0.022%

    No Known Activations