© 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. 30041
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating ability or possibility

    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
    RTDA
    -0.66
     sape
    -0.63
     quæ
    -0.59
     nudo
    -0.58
     agences
    -0.58
     Could
    -0.57
     entanto
    -0.56
     voorkomen
    -0.56
    avais
    -0.54
     übrigens
    -0.54
    POSITIVE LOGITS
     ويكيميديا
    1.09
    IntoConstraints
    0.79
    PerformLayout
    0.76
    
    0.68
     архивлан
    0.67
     okuyayım
    0.66
     Wicidata
    0.65
    Datuak
    0.64
    +#+#
    0.63
     createContext
    0.60
    Activations Density 0.021%

    No Known Activations