© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 1237
    Prev
    Next
    INDEX
    Explanations

    enthusiastic language expressing excitement for crafting hobbies

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
     fucking
    -0.82
     fucked
    -0.82
     אתה
    -0.77
    אתה
    -0.75
    Bullshit
    -0.74
     rád
    -0.73
    ผม
    -0.73
     fuckin
    -0.73
     fuck
    -0.72
     shit
    -0.71
    POSITIVE LOGITS
     hubby
    0.87
     suami
    0.71
     etsy
    0.65
     esposo
    0.64
     husband
    0.62
     Etsy
    0.62
    husband
    0.61
     Pinterest
    0.61
     pinterest
    0.61
     postpartum
    0.60
    Activations Density 1.783%

    No Known Activations