© 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. 24-RES-MATRYOSHKA-DC
    7. 765
    Prev
    Next
    INDEX
    Explanations

    scientific studies.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
    ِّف
    -0.61
    CppMethod
    -0.60
     doInBackground
    -0.59
     numberWith
    -0.59
    OGND
    -0.57
    TintMode
    -0.57
     >=",
    -0.57
     média
    -0.56
    RequestHandler
    -0.54
    WebServlet
    -0.54
    POSITIVE LOGITS
     spectra
    0.79
     XPS
    0.71
     XRD
    0.70
     FTIR
    0.67
    XRD
    0.66
    spectra
    0.64
     measurements
    0.62
    FTIR
    0.62
    TGA
    0.61
     TGA
    0.60
    Activations Density 1.036%

    No Known Activations