© 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. 24098
    Prev
    Next
    INDEX
    Explanations

    instances of the word "somehow" and variations of it

    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
    Negative Logits
     Daly
    -0.66
     Yen
    -0.64
     []:
    -0.60
    Eliza
    -0.57
     McGrath
    -0.56
     setDate
    -0.56
     onStop
    -0.56
    PreExecute
    -0.56
     Wikimedijinoj
    -0.55
    fromnode
    -0.54
    POSITIVE LOGITS
    tagHelperRunner
    0.81
     magically
    0.79
    FieldBuilder
    0.79
    Somehow
    0.77
     newBuilder
    0.75
     gynhyrchwyd
    0.72
     Somehow
    0.72
    KommentareTeilen
    0.71
    لينكات
    0.70
    MigrationBuilder
    0.70
    Activations Density 0.004%

    No Known Activations