© 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. 18-RES-MATRYOSHKA-DC
    7. 703
    Prev
    Next
    INDEX
    Explanations

    pronouns and terms referring to systems and finance.

    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.18.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.18.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
     Efq
    -0.73
     EconPapers
    -0.69
    endphp
    -0.66
     myſelf
    -0.65
    ftagPool
    -0.65
     onAnimation
    -0.64
    HtmlAttribute
    -0.61
    PerformLayout
    -0.59
     ſy
    -0.59
     صوتيه
    -0.59
    POSITIVE LOGITS
     meaning
    2.39
     means
    2.34
    means
    2.09
     mean
    2.09
    meaning
    2.03
     refers
    2.02
     MEAN
    2.00
     Meaning
    1.99
    Meaning
    1.98
     Means
    1.91
    Activations Density 1.703%

    No Known Activations