© 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
    2. Gemma-2-2B
    3. 22-RES-MATRYOSHKA-DC
    4. 2345
    Prev
    Next
    INDEX
    Explanations

    a mix of animal sounds, political figures, and references to publications/reports/issues.

    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
    GEBURTSDATUM
    -0.91
    "):
    
    -0.88
    .")
    
    -0.85
    DispatchToProps
    -0.83
    complexContent
    -0.81
     }{@
    -0.79
    رشف
    -0.77
    TypedDataSet
    -0.77
    */;
    -0.76
     OFDb
    -0.76
    POSITIVE LOGITS
    !
    3.22
    !"
    2.39
    !”
    2.36
    !)
    2.36
    !!
    2.25
    !
    2.23
     !
    2.23
    !’
    2.19
    !</
    2.16
    !'
    2.14
    Activations Density 0.730%

    No Known Activations