© 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. 32055
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or disbelief

    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
     myſelf
    -0.78
    
    -0.76
    Ārējās
    -0.69
     resourceCulture
    -0.65
     itſelf
    -0.65
     Stande
    -0.65
     Nonetheless
    -0.65
     uovo
    -0.65
     Diſ
    -0.64
     Pourtant
    -0.64
    POSITIVE LOGITS
     caisse
    0.59
    pexpr
    0.59
    bledon
    0.54
    /-/
    0.54
    esthes
    0.53
     Cake
    0.52
    olol
    0.51
     Dai
    0.50
    cieli
    0.49
    atmosfera
    0.49
    Activations Density 0.011%

    No Known Activations