© 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. 22-RES-MATRYOSHKA-DC
    7. 1753
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to transactions or movement of information/materials

    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
    ätzlich
    -0.58
     &___
    -0.57
    expandindo
    -0.55
    ofür
    -0.52
     autorytatywna
    -0.51
    ohist
    -0.51
    yeth
    -0.50
    idhi
    -0.50
    ၌
    -0.50
    chere
    -0.49
    POSITIVE LOGITS
     from
    3.41
    from
    2.53
     från
    2.17
     FROM
    2.16
    จาก
    2.11
     từ
    2.02
     dari
    1.99
    From
    1.97
     From
    1.95
     kutoka
    1.77
    Activations Density 4.239%

    No Known Activations