© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 708
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas, chemical formulas or URLs that contain numbers and punctuation

    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.22.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.22.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
     ―――――
    -0.66
     Majefty
    -0.62
     Jefus
    -0.59
     Monfieur
    -0.58
     myſelf
    -0.57
     Theſe
    -0.56
    wiſe
    -0.54
     setTotal
    -0.54
     perfons
    -0.52
    ſſel
    -0.50
    POSITIVE LOGITS
    }{*}{
    0.81
    ftagPool
    0.78
    WriteLiteral
    0.74
     '\\;'
    0.68
    msub
    0.65
    Pyx
    0.63
    SBATCH
    0.63
    يكب
    0.63
    Geplaatst
    0.61
    OGND
    0.61
    Activations Density 1.524%

    No Known Activations