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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11466
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in data representation, particularly in statistical or tabular formats

    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
    τερα
    -0.58
    脚注の使い方
    -0.56
    发表于
    -0.55
    canestro
    -0.53
     referrerpolicy
    -0.52
    APORE
    -0.52
    esModule
    -0.51
    fél
    -0.51
     Réponses
    -0.50
    UTERS
    -0.49
    POSITIVE LOGITS
    ]='\
    0.85
    imageio
    0.52
     defaultstate
    0.51
    HasForeignKey
    0.50
    """
    0.50
    Legături
    0.49
    RenderAtEndOf
    0.48
    (/[
    0.48
    mailto
    0.48
    aarrggbb
    0.48
    Activations Density 0.048%

    No Known Activations