© 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. 8756
    Prev
    Next
    INDEX
    Explanations

    references to ceilings and overhead views

    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
    Stepper
    -0.68
    toje
    -0.63
     åt
    -0.62
    рби
    -0.60
     makeStyles
    -0.57
     FORMA
    -0.57
     willful
    -0.57
     âgées
    -0.57
    stepper
    -0.56
     ‘
    -0.56
    POSITIVE LOGITS
     ceiling
    1.48
    Ceiling
    1.47
     Ceiling
    1.45
     ceilings
    1.43
    ceiling
    1.34
     Overhead
    1.23
     overhead
    1.20
    Overhead
    1.16
    overhead
    1.14
     Decken
    0.96
    Activations Density 0.002%

    No Known Activations