© 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. 15349
    Prev
    Next
    INDEX
    Explanations

    repeated phrases emphasizing inclusivity or totality

    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
     Meksiku
    -0.93
    Portale
    -0.86
     beginnetje
    -0.75
    StructEnd
    -0.71
    最快更新
    -0.69
    uxxxx
    -0.69
    AutoScaleMode
    -0.68
    addContainerGap
    -0.68
    LookAnd
    -0.66
    cestry
    -0.66
    POSITIVE LOGITS
     the
    0.79
     BoxDecoration
    0.67
     that
    0.59
     something
    0.57
     sådan
    0.53
     a
    0.52
     like
    0.52
     tým
    0.52
     of
    0.50
     this
    0.50
    Activations Density 0.027%

    No Known Activations