© 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. 26979
    Prev
    Next
    INDEX
    Explanations

    negative expressions or terms associated with negativity

    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
     kasarigan
    -0.75
    +#+#
    -0.68
    """.
    -0.64
    consulté
    -0.59
     ddelweddau
    -0.59
     Greeks
    -0.58
    imageshack
    -0.57
    تيجة
    -0.56
    logous
    -0.55
    mbals
    -0.54
    POSITIVE LOGITS
     estekak
    0.71
    ChildScrollView
    0.59
    fillType
    0.54
    ClientRect
    0.54
    TextAppearance
    0.52
    SourceChecksum
    0.49
     अलावा
    0.49
     Lynd
    0.48
    DrawerToggle
    0.48
    XmlAccessorType
    0.48
    Activations Density 0.034%

    No Known Activations