© 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. 18-RES-MATRYOSHKA-DC
    7. 828
    Prev
    Next
    INDEX
    Explanations

    the adverb "often" followed by a verb

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     possibly
    -0.90
     potentially
    -0.82
    potentially
    -0.71
    possibly
    -0.70
     hopefully
    -0.69
     conceivably
    -0.69
     posiblemente
    -0.69
    CloseOperation
    -0.65
     basically
    -0.65
    そろそろ
    -0.63
    POSITIVE LOGITS
     бывает
    0.96
     referred
    0.71
     bý
    0.69
     overlooked
    0.69
    情况下
    0.68
     accompanied
    0.68
    referred
    0.68
     referido
    0.67
     accompanies
    0.67
    times
    0.67
    Activations Density 1.252%

    No Known Activations