© 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. 542
    Prev
    Next
    INDEX
    Explanations

    seemingly random words in the text

    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
    ➯
    -0.39
     Copernicus
    -0.36
     مرئيه
    -0.35
     '\\;'
    -0.32
    iedenen
    -0.32
    Stéphane
    -0.31
     Bailly
    -0.31
    engibre
    -0.31
     Normdatei
    -0.30
    Ár
    -0.30
    POSITIVE LOGITS
     l
    1.08
    L
    0.95
    getL
    0.88
     li
    0.87
     L
    0.86
     lc
    0.85
    l
    0.85
     lp
    0.84
    ｌ
    0.84
     ls
    0.83
    Activations Density 4.484%

    No Known Activations