© 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. 30949
    Prev
    Next
    INDEX
    Explanations

    phrases indicating frequency or conditions regarding events or actions

    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
    Obrigada
    -0.52
    onade
    -0.51
    وردار
    -0.48
    nac
    -0.48
     numberWith
    -0.47
     ACKNOWLEDG
    -0.47
    enseits
    -0.47
    ostom
    -0.46
     Occidente
    -0.46
    momix
    -0.45
    POSITIVE LOGITS
    ⓧ
    0.88
    SharedCtor
    0.87
     lenker
    0.83
     كومونز
    0.82
    GEBURTSDATUM
    0.75
    IUrlHelper
    0.75
    CppMethod
    0.73
    :✨
    0.70
    Personensuche
    0.69
     IBOutlet
    0.69
    Activations Density 0.130%

    No Known Activations