© 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. 2258
    Prev
    Next
    INDEX
    Explanations

    the word "auto" or "Auto" followed by a hyphen and other text

    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
    ParallelGroup
    -0.56
    MergeFrom
    -0.54
     cardiaque
    -0.54
     "..\..\..\
    -0.54
     }}"></
    -0.52
    MessageInfo
    -0.52
     Alpes
    -0.52
    Jeografia
    -0.51
     professionale
    -0.47
     genoeg
    -0.47
    POSITIVE LOGITS
     Auto
    0.93
     AUTO
    0.92
     Autos
    0.89
    setAuto
    0.82
     auto
    0.81
    Auto
    0.77
    Autos
    0.77
     defaultstate
    0.76
    autos
    0.73
    autoconfigure
    0.72
    Activations Density 0.058%

    No Known Activations