© 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. 2794
    Prev
    Next
    INDEX
    Explanations

    verbs indicating past actions or experiences

    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
    weapons
    -0.79
     pist
    -0.79
    atchewan
    -0.76
    kenny
    -0.75
    таратура
    -0.75
     Raquel
    -0.75
     Worcester
    -0.74
    ächs
    -0.73
     twe
    -0.70
    Weapons
    -0.70
    POSITIVE LOGITS
    s
    1.11
    dad
    0.74
     hoped
    0.73
    WithIOException
    0.71
     Bür
    0.69
     Hadley
    0.67
    Αν
    0.67
     chaud
    0.66
     HAD
    0.66
    INCREF
    0.66
    Activations Density 0.211%

    No Known Activations