© 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. 26491
    Prev
    Next
    INDEX
    Explanations

    the presence of download-related information and instructions for games

    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
     iſt
    -0.81
     auffi
    -0.74
     ainfi
    -0.72
     itſelf
    -0.72
    󠁢
    -0.72
     (\<
    -0.68
     Hilo
    -0.68
     photolibrary
    -0.67
     myſelf
    -0.67
     ſy
    -0.66
    POSITIVE LOGITS
     
    0.65
    ↵
    0.57
     Robert
    0.57
    <eos>
    0.55
     ...
    0.54
    Билгалдахарш
    0.54
     is
    0.53
     та
    0.52
    ↵↵
    0.51
     s
    0.50
    Activations Density 0.001%

    No Known Activations