© 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. 2155
    Prev
    Next
    INDEX
    Explanations

    words related to reviews and assessments of a project or performance

    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
     Надо
    -0.91
     (;;)
    -0.90
    Надо
    -0.88
     jedenfalls
    -0.85
     daß
    -0.83
    essentiel
    -0.78
     надо
    -0.75
     geleg
    -0.73
     offenbar
    -0.72
     fubject
    -0.72
    POSITIVE LOGITS
     hierbei
    0.89
    Utiliz
    0.84
     possu
    0.81
     posiada
    0.78
    Utili
    0.77
     demnach
    0.77
     welcher
    0.77
     данного
    0.77
     Utilize
    0.76
     utilizing
    0.76
    Activations Density 1.713%

    No Known Activations