© 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. 8517
    Prev
    Next
    INDEX
    Explanations

    keywords related to scientific evidence and relationships in biological contexts

    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
     propOrder
    -0.68
     snippetHide
    -0.63
    ftagPool
    -0.62
     onPostExecute
    -0.60
     مشين
    -0.58
    ViewFeatures
    -0.57
    सन्दर्भ
    -0.56
    IUrlHelper
    -0.56
    LookAnd
    -0.56
     Roskov
    -0.56
    POSITIVE LOGITS
    mybatisplus
    0.60
     aceptas
    0.59
    InSection
    0.56
     compartilhar
    0.55
    azzo
    0.52
    lase
    0.52
    原始内容存档于
    0.51
    voorbeeld
    0.48
    seamnă
    0.48
     Tecnologia
    0.47
    Activations Density 0.337%

    No Known Activations