© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 3891
    Prev
    Next
    INDEX
    Explanations

    words related to events and outcomes

    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
     Djibouti
    -0.85
     étrangère
    -0.81
    PreferredItem
    -0.77
     piú
    -0.77
    ibouti
    -0.76
     StringVar
    -0.76
    RetentionPolicy
    -0.74
     Heine
    -0.73
     vectorielle
    -0.72
     grecque
    -0.72
    POSITIVE LOGITS
     HAPP
    1.34
     happen
    1.34
     happened
    1.31
     Happen
    1.27
     happens
    1.24
     happening
    1.21
     Happens
    1.20
     Happened
    1.18
    happen
    1.17
    happened
    1.16
    Activations Density 0.042%

    No Known Activations