© 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. 18-RES-MATRYOSHKA-DC
    7. 20
    Prev
    Next
    INDEX
    Explanations

    words related to asserting opinions, making arguments, observations, or drawing conclusions

    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.18.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.18.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
    quels
    -0.65
     ویکی‌آمباردا
    -0.63
     Италијани
    -0.59
    >");
    -0.58
    autique
    -0.56
    bewerken
    -0.56
    /−
    -0.54
     otomatig
    -0.54
     ?>/
    -0.53
     ویکی‌پدیای
    -0.52
    POSITIVE LOGITS
     that
    2.14
     bahwa
    1.63
     rằng
    1.37
     ότι
    1.26
    ว่า
    1.12
     bahawa
    1.11
     πως
    0.99
    that
    0.98
     kwamba
    0.90
     că
    0.87
    Activations Density 3.434%

    No Known Activations