© 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. 2232
    Prev
    Next
    INDEX
    Explanations

    terms related to biological classification and characteristics of species, particularly indigenous species and their habitats

    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
    ViewImports
    -0.56
    ViewChild
    -0.47
     TextAppearance
    -0.46
    koc
    -0.46
     Transfermarkt
    -0.45
     *>(
    -0.45
     gainera
    -0.44
    ərbaycan
    -0.43
     phụ
    -0.42
     Waterford
    -0.42
    POSITIVE LOGITS
    IVEREF
    0.79
    +#+
    0.74
    webElementXpaths
    0.68
    parsedMessage
    0.66
    معلومات
    0.59
    MessageTagHelper
    0.58
     entanto
    0.56
    MNA
    0.56
    UnsafeEnabled
    0.55
    цездатний
    0.54
    Activations Density 1.412%

    No Known Activations