© 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. 30299
    Prev
    Next
    INDEX
    Explanations

    references to roles and performances in acting

    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
    ^(@)
    -0.79
     itſelf
    -0.69
     neceff
    -0.69
    BufferException
    -0.68
     whofe
    -0.64
     raiſ
    -0.63
    !")
    -0.63
    ."));
    -0.63
     whoſe
    -0.61
     occafion
    -0.60
    POSITIVE LOGITS
    cshtml
    0.66
    Personensuche
    0.63
    webElementXpaths
    0.54
    rungsseite
    0.52
    Initializable
    0.52
    AttributeSet
    0.51
    fhir
    0.51
    InSection
    0.51
     shui
    0.50
    paying
    0.50
    Activations Density 0.014%

    No Known Activations