© 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. 8844
    Prev
    Next
    INDEX
    Explanations

    latex mathematical expressions related to functions or equations

    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
    коли
    -0.51
    }$$
    -0.48
    orique
    -0.47
    :
    -0.47
    spanning
    -0.47
    slash
    -0.47
    sof
    -0.46
    ništvo
    -0.45
    ništ
    -0.45
     research
    -0.45
    POSITIVE LOGITS
     ویکی‌پدیای
    0.84
     FetchType
    0.79
    enumi
    0.68
    enumii
    0.68
    شهاد
    0.61
    醐
    0.61
    AddHtmlAttribute
    0.60
     lenker
    0.58
    libft
    0.57
    tvguidetime
    0.57
    Activations Density 0.019%

    No Known Activations