© 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. 16393
    Prev
    Next
    INDEX
    Explanations

    the word "hand" in various contexts

    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
    DockStyle
    -0.83
    <!--[
    -0.80
    CrossRef
    -0.75
    >−
    -0.73
    resizingMask
    -0.72
    istoitu
    -0.72
    HasForeignKey
    -0.71
     typelib
    -0.69
     WaitForSeconds
    -0.68
    GeneratedValue
    -0.67
    POSITIVE LOGITS
     Eles
    0.61
    áy
    0.58
    empres
    0.56
     McE
    0.55
     Horv
    0.55
    urunan
    0.55
     Anak
    0.54
     Stallion
    0.54
    avra
    0.53
     "..\..\..\
    0.53
    Activations Density 0.007%

    No Known Activations