© 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. 3533
    Prev
    Next
    INDEX
    Explanations

    conditional statements or phrases

    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
     when
    -0.77
     gdy
    -0.73
    when
    -0.62
     quando
    -0.60
     cuando
    -0.60
     تعدى
    -0.59
     there
    -0.56
    mayın
    -0.56
     Trost
    -0.56
     depending
    -0.55
    POSITIVE LOGITS
    Aiheesta
    0.66
     nakalista
    0.60
    migrationBuilder
    0.60
    ("}");
    0.59
     Normdatei
    0.59
    Grüße
    0.58
    localVar
    0.55
    paroles
    0.55
     könnt
    0.54
    %)$
    0.53
    Activations Density 0.058%

    No Known Activations