© 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. 22-RES-MATRYOSHKA-DC
    7. 3012
    Prev
    Next
    INDEX
    Explanations

    phrases that are combinations of prepositions and quantifiers followed by "circumstances"

    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.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    UnusedPrivate
    -0.63
    IsContent
    -0.60
    Tikang
    -0.60
    migrationBuilder
    -0.60
    ngrx
    -0.57
    ⓧ
    -0.55
    NegativeButton
    -0.55
    PerformLayout
    -0.54
     ModelExpression
    -0.53
    @[+][
    -0.52
    POSITIVE LOGITS
     circumstances
    1.95
     Circumstances
    1.68
     situation
    1.64
    circum
    1.59
     circonstances
    1.58
     circumstance
    1.56
    situation
    1.52
     Situation
    1.44
     SITUATION
    1.43
     situations
    1.41
    Activations Density 0.489%

    No Known Activations