© 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. 22-RES-MATRYOSHKA-DC
    7. 1769
    Prev
    Next
    INDEX
    Explanations

    phrases related to filmmaking and economic theory

    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
     hierbei
    -1.19
     poichè
    -0.99
     می‌باشد
    -0.98
     данного
    -0.97
     welches
    -0.97
     içerisinde
    -0.94
    Whilst
    -0.94
     Whilst
    -0.93
     utilizing
    -0.93
    非常的
    -0.91
    POSITIVE LOGITS
     freilich
    1.04
    eabouts
    0.91
     cheerfully
    0.87
     commonest
    0.83
     jedenfalls
    0.83
     stuff
    0.82
     lousy
    0.81
    <_>
    0.79
    Пото
    0.79
     היתה
    0.79
    Activations Density 3.459%

    No Known Activations