© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1281
    Prev
    Next
    INDEX
    Explanations

    code-related terms, including functions, files, and properties.

    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
    _
    -0.79
    -
    -0.66
     op
    -0.65
     a
    -0.65
     so
    -0.62
     her
    -0.61
     
    -0.61
     «
    -0.60
     v
    -0.57
     ri
    -0.57
    POSITIVE LOGITS
     Monfieur
    1.33
     Majefty
    1.25
     itſelf
    1.24
     Houſe
    1.20
     Reſ
    1.19
     myſelf
    1.18
    ſelves
    1.17
     Jefus
    1.17
     Anſ
    1.16
     Diſ
    1.14
    Activations Density 1.143%

    No Known Activations