© 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. 8421
    Prev
    Next
    INDEX
    Explanations

    the word "part."

    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
    󠁿
    -0.68
    +#+#
    -0.65
    MetaObject
    -0.63
    tableFuture
    -0.61
     ansiedade
    -0.59
     jouets
    -0.58
     Wikidata
    -0.57
    WithIOException
    -0.57
     affaires
    -0.57
     Winfrey
    -0.57
    POSITIVE LOGITS
    ESTRE
    0.76
    LEncoder
    0.68
    adalu
    0.67
    Према
    0.66
     pre
    0.65
    LayoutInflater
    0.65
    antel
    0.65
     Henn
    0.65
    jarati
    0.65
     htmlFor
    0.64
    Activations Density 0.008%

    No Known Activations