© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 214
    Prev
    Next
    INDEX
    Explanations

    structure or elements associated with code or programming syntax

    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
    makeatother
    -0.79
    CUR
    -0.69
     MX
    -0.68
    ONAUT
    -0.67
     Christy
    -0.66
    libft
    -0.64
     AX
    -0.63
    Muster
    -0.63
    ⋱
    -0.63
    lovakia
    -0.63
    POSITIVE LOGITS
    ViewFeatures
    0.98
    \{\\
    0.89
    mrow
    0.85
     VIDEOTAPE
    0.65
    Obrázky
    0.63
    ositol
    0.60
    GEBURTSDATUM
    0.58
    iconque
    0.57
    Anhalt
    0.56
     nakalista
    0.55
    Activations Density 0.794%

    No Known Activations