© 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. 283
    Prev
    Next
    INDEX
    Explanations

    phrases and common words that indicate importance or connection

    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
    Билгалдахарш
    -0.69
    MLLoader
    -0.62
    bolistas
    -0.59
    artige
    -0.58
    BuildContext
    -0.57
     tertentu
    -0.56
     betreffende
    -0.55
    httphttps
    -0.54
    __":
    -0.54
    Przypisy
    -0.53
    POSITIVE LOGITS
     source
    1.02
     cornerstone
    0.97
     mainstay
    0.95
     catalyst
    0.89
     stepping
    0.89
     means
    0.87
     centerpiece
    0.82
     tool
    0.81
     focal
    0.80
     main
    0.79
    Activations Density 2.184%

    No Known Activations