© 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. 18552
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or claims related to evidence

    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
     الرياضيه
    -0.85
     NTIS
    -0.81
     photolibrary
    -0.78
     RequestMethod
    -0.77
    complexContent
    -0.74
     Himo
    -0.72
    standers
    -0.72
    CloseOperation
    -0.72
     Borel
    -0.71
    cheme
    -0.71
    POSITIVE LOGITS
     we
    0.84
     they
    0.79
     it
    0.79
     he
    0.73
     there
    0.72
     if
    0.66
     you
    0.66
     T
    0.64
     I
    0.62
     colpo
    0.61
    Activations Density 0.135%

    No Known Activations