© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3009
    Prev
    Next
    INDEX
    Explanations

    the word "most" 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
    rungsseite
    -0.92
    LEncoder
    -0.85
    ANDUM
    -0.67
    quele
    -0.66
    DrawerToggle
    -0.65
    neries
    -0.64
    ilation
    -0.63
    IRC
    -0.63
     Kalk
    -0.63
    beke
    -0.63
    POSITIVE LOGITS
     MIST
    0.77
     flesta
    0.72
     bross
    0.70
    ConstraintLayout
    0.69
    most
    0.69
     MOST
    0.69
    webElementXpaths
    0.69
    ostante
    0.68
    MOST
    0.68
     lahat
    0.68
    Activations Density 0.043%

    No Known Activations