© 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. 20310
    Prev
    Next
    INDEX
    Explanations

    negative expressions related to conditions or limitations

    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
    +#+#
    -0.82
    TintMode
    -0.62
     VIDEOTAPE
    -0.58
    ThroughAttribute
    -0.56
    หวัด
    -0.52
     disambiguazione
    -0.51
    .*")]
    -0.51
     sputnik
    -0.51
     estimés
    -0.50
    webElement
    -0.48
    POSITIVE LOGITS
     meanwhile
    0.66
     ContentValues
    0.66
     nevertheless
    0.57
    atorul
    0.54
    zler
    0.53
    ंत
    0.53
    — 
    0.53
    ficado
    0.53
    TestBed
    0.52
    NewGuid
    0.52
    Activations Density 0.109%

    No Known Activations