© 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. 26627
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to" and similar directional or transitional phrases

    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
    AllowUser
    -0.87
    __/
    -0.83
    таратура
    -0.81
     saites
    -0.80
     AssemblyTitle
    -0.76
    isissez
    -0.75
    JNIEnv
    -0.75
    neath
    -0.74
     the
    -0.73
     distanciation
    -0.72
    POSITIVE LOGITS
    TO
    1.13
    to
    1.08
     Toh
    0.98
    Ato
    0.93
    To
    0.92
     TO
    0.83
     stomat
    0.82
    то
    0.80
     Topeka
    0.80
     Ato
    0.77
    Activations Density 0.090%

    No Known Activations