© 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. 1092
    Prev
    Next
    INDEX
    Explanations

    general words such as "What, Are, Reviews, So, That, Something", that are used in many different context in the the document.

    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
    ेशा
    -0.68
    ')['
    -0.56
     Administrativna
    -0.52
     njego
    -0.50
    dalena
    -0.48
     بگیر
    -0.48
    setVerticalGroup
    -0.48
    imageshack
    -0.47
    enterian
    -0.47
    κέ
    -0.47
    POSITIVE LOGITS
     we
    3.25
     our
    2.69
    我們
    2.53
     ourselves
    2.52
    我们
    2.48
    We
    2.39
     We
    2.30
     nous
    2.13
     我们
    2.11
     мы
    2.09
    Activations Density 2.720%

    No Known Activations