© 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. 22-RES-MATRYOSHKA-DC
    7. 3107
    Prev
    Next
    INDEX
    Explanations

    words indicating negative impact on people or places

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ThroughAttribute
    -0.80
    RRect
    -0.68
    awtextra
    -0.64
    MethodManager
    -0.63
     myſelf
    -0.63
    StoryboardSegue
    -0.60
     transfieras
    -0.59
     Monfieur
    -0.58
    oredCriteria
    -0.57
    ✭✭
    -0.57
    POSITIVE LOGITS
     affected
    2.55
     Affected
    2.19
    affected
    2.14
    Affected
    2.05
     impacted
    2.03
     afectada
    1.59
     AFFECT
    1.59
     afectado
    1.55
     afectados
    1.53
     afectadas
    1.51
    Activations Density 1.026%

    No Known Activations