© 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. 1012
    Prev
    Next
    INDEX
    Explanations

    first-person attempts to perform computing, succeeding or failing

    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
     conceivably
    -0.57
     subsequently
    -0.53
    IsContent
    -0.52
     likewise
    -0.52
     للتو
    -0.52
     økonom
    -0.51
    UnusedPrivate
    -0.50
     hendes
    -0.48
    HtmlAttribute
    -0.48
     admittedly
    -0.48
    POSITIVE LOGITS
     gonna
    0.76
     GONNA
    0.71
     Gonna
    0.66
     loose
    0.62
     survie
    0.61
     advice
    0.60
     resourceCulture
    0.60
     aidant
    0.60
     avoit
    0.59
     comeback
    0.59
    Activations Density 1.118%

    No Known Activations