© 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. 607
    Prev
    Next
    INDEX
    Explanations

    content in online messaging

    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
    enumi
    -0.62
    WriteTagHelper
    -0.49
    ".
    -0.41
    GEBURTSDATUM
    -0.41
    Needless
    -0.38
     Maintenant
    -0.38
    当我
    -0.38
     Sd
    -0.37
     GOS
    -0.37
    Maintenant
    -0.36
    POSITIVE LOGITS
     yep
    0.99
    なるほど
    0.92
    yep
    0.91
    indeed
    0.91
     yeah
    0.90
     yup
    0.87
     hmm
    0.87
    yup
    0.86
    yeah
    0.85
     Yep
    0.85
    Activations Density 0.229%

    No Known Activations