© 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. 15764
    Prev
    Next
    INDEX
    Explanations

    future tense verbs indicating intention or certainty

    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
    AddTagHelper
    -0.94
     MainAxisSize
    -0.86
    ContentAlignment
    -0.77
     متعلقه
    -0.76
    ftagPool
    -0.73
    MigrationBuilder
    -0.70
    تقاوى
    -0.69
     beginnetje
    -0.68
    adaptiveStyles
    -0.67
    BASELINE
    -0.67
    POSITIVE LOGITS
    bed
    0.61
     itself
    0.54
    atitis
    0.53
    使
    0.52
     himself
    0.52
     timeType
    0.51
     themselves
    0.50
     contributed
    0.49
    น์
    0.49
     wrestling
    0.49
    Activations Density 0.008%

    No Known Activations