© 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. 25796
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance and impact in visual effects or shaders

    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
     disambiguazione
    -0.83
    PYX
    -0.70
    сылкі
    -0.69
     виправивши
    -0.68
     isComment
    -0.67
    SuccessListener
    -0.66
    فایل‌لار
    -0.65
     continuant
    -0.65
    harp
    -0.62
    AutoScale
    -0.61
    POSITIVE LOGITS
    :
    0.75
    :
    0.70
    Einzelnachweise
    0.70
    __":
    0.67
    __':
    0.67
    ?:
    0.63
    :\
    0.62
    $:
    0.60
    :</
    0.57
    ":{"
    0.57
    Activations Density 0.062%

    No Known Activations