© 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. 315
    Prev
    Next
    INDEX
    Explanations

    cascading style sheets (CSS) code

    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
     jsPsych
    -0.57
     Arque
    -0.54
    công
    -0.52
     Head
    -0.51
    numbered
    -0.50
     TITLE
    -0.49
    numerusform
    -0.49
    lehrer
    -0.48
     cser
    -0.48
    TestingModule
    -0.48
    POSITIVE LOGITS
    position
    0.72
    display
    0.71
    margin
    0.70
    background
    0.67
     position
    0.66
    padding
    0.65
    rawDesc
    0.64
    border
    0.62
     display
    0.61
    font
    0.60
    Activations Density 0.164%

    No Known Activations