© 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. 29553
    Prev
    Next
    INDEX
    Explanations

    references to poly(ADP-ribose) polymerase (PARP) in the context of cellular processes

    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
     endfor
    -0.77
    PutMapping
    -0.76
     kasarigan
    -0.75
     Roskov
    -0.73
    Datuak
    -0.66
     doubtnut
    -0.66
     CYTHON
    -0.65
     poffe
    -0.65
     Viro
    -0.64
    extAlignment
    -0.64
    POSITIVE LOGITS
    навли
    0.66
    MethodManager
    0.65
    PARAMS
    0.55
     params
    0.51
    DataAnnotations
    0.50
    ostom
    0.48
    ArgumentParser
    0.47
    ADP
    0.47
    ỏng
    0.47
     disambiguazione
    0.47
    Activations Density 0.002%

    No Known Activations