© 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. 1789
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce examples or are related to specifics.

    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
    TagMode
    -0.66
     astfel
    -0.57
     createSlice
    -0.57
     wikipagina
    -0.55
     چنین
    -0.53
    ₂+
    -0.53
    Controllo
    -0.53
     weder
    -0.51
     NgModule
    -0.51
     ModelExpression
    -0.50
    POSITIVE LOGITS
     those
    1.30
    those
    1.15
     ones
    1.08
     quelli
    1.08
     celles
    1.05
    Those
    0.98
     Those
    0.96
     ceux
    0.95
     THOSE
    0.93
     celle
    0.93
    Activations Density 1.790%

    No Known Activations