© 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. 8490
    Prev
    Next
    INDEX
    Explanations

    terms related to reducing or eliminating negative effects or deficiencies

    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
     Meksiku
    -0.85
    Биография
    -0.66
     ویکی‌پدی
    -0.66
    ValueGeneration
    -0.65
     StatefulWidget
    -0.64
    دانشنامهٔ
    -0.61
    archiviato
    -0.59
     Parcelable
    -0.59
    UserScript
    -0.59
     Normdatei
    -0.58
    POSITIVE LOGITS
    æt
    0.51
    ulturen
    0.47
    ætte
    0.46
    apuram
    0.46
    uncher
    0.46
    aporation
    0.46
     thunk
    0.46
     Kendall
    0.46
     Elbe
    0.46
     contributo
    0.46
    Activations Density 0.058%

    No Known Activations