© 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. 10282
    Prev
    Next
    INDEX
    Explanations

    concepts related to justification and reasoning for conflict or actions based on perceived threats

    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
     greateſt
    -0.71
     itſelf
    -0.63
     pleaſure
    -0.63
    QMetaType
    -0.60
     laſt
    -0.59
    ModelSerializer
    -0.59
     Reſ
    -0.59
    apé
    -0.57
    Pozri
    -0.57
    AuthProvider
    -0.57
    POSITIVE LOGITS
    Autoritní
    0.68
    IsContent
    0.56
    Hentet
    0.46
     MessageBoxIcon
    0.46
    MemoryWarning
    0.44
    exitRule
    0.44
    
    0.43
    ArgsConstructor
    0.43
     Signalez
    0.43
     Wicidata
    0.43
    Activations Density 0.242%

    No Known Activations