© 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. 29646
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "case" in various contexts

    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
    ]")]
    -0.95
    okovic
    -0.82
    visiae
    -0.81
    ximately
    -0.80
    BeforeMethod
    -0.76
     ​​
    -0.75
     endfor
    -0.74
    hdashline
    -0.73
    hirts
    -0.71
    endfor
    -0.71
    POSITIVE LOGITS
    tadır
    0.60
     preparations
    0.60
     Schla
    0.58
    ásticos
    0.58
    Eme
    0.57
     resto
    0.57
     János
    0.57
    óny
    0.56
    Ass
    0.56
     plans
    0.56
    Activations Density 0.009%

    No Known Activations