© 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. 12-RES-MATRYOSHKA-DC
    7. 30312
    Prev
    Next
    INDEX
    Explanations

    the term "bear" and its variations in different 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
    adaptiveStyles
    -1.02
    Obrázky
    -0.78
    tonsoft
    -0.77
    uesday
    -0.76
     jadx
    -0.76
    othesis
    -0.76
     незавершена
    -0.75
    prefixer
    -0.74
     Alvin
    -0.74
     تانيه
    -0.74
    POSITIVE LOGITS
     bears
    1.84
     bear
    1.70
     Bears
    1.67
     Bear
    1.66
    Bear
    1.66
    bear
    1.65
     BEAR
    1.63
    Bears
    1.40
    BEAR
    1.37
     bearing
    1.30
    Activations Density 0.015%

    No Known Activations