© 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. 3813
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting elements such as brackets and fractions

    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
     fore
    -0.54
    TAWA
    -0.46
     ha
    -0.46
     form
    -0.42
    isable
    -0.42
    berra
    -0.42
     try
    -0.42
    バリ
    -0.41
     assume
    -0.40
    ようになりました
    -0.39
    POSITIVE LOGITS
     Meksiku
    0.80
     kaarangay
    0.77
     beginnetje
    0.72
    ISupport
    0.72
    hdashline
    0.72
    OrNil
    0.70
    Хьажоргаш
    0.68
    RTLU
    0.68
    AutoScaleMode
    0.68
     enfans
    0.67
    Activations Density 0.016%

    No Known Activations