© 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. 2389
    Prev
    Next
    INDEX
    Explanations

    negative numbers and section numbers

    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
     Godt
    -0.53
    publicain
    -0.51
     Wolfram
    -0.50
     Horns
    -0.49
    örg
    -0.48
     deportivos
    -0.48
    RenderAtEndOf
    -0.47
     gerais
    -0.47
    og
    -0.46
     Republican
    -0.46
    POSITIVE LOGITS
     препратки
    0.65
    IVEREF
    0.65
    EndInit
    0.61
    ContentAsync
    0.60
    windowFixed
    0.56
    Enlaces
    0.54
    MLLoader
    0.54
     answers
    0.53
     Answered
    0.53
    esez
    0.51
    Activations Density 0.226%

    No Known Activations