© 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. 24-RES-MATRYOSHKA-DC
    7. 110
    Prev
    Next
    INDEX
    Explanations

    the boilerplate text of an Apache software license

    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.24.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.24.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
    tvguidetime
    -1.12
    RenderAtEndOf
    -1.05
     Efq
    -1.05
     Мексичка
    -1.02
     GenerationType
    -1.01
    parsedMessage
    -0.95
    IUrlHelper
    -0.95
    expandindo
    -0.93
     виправивши
    -0.92
     JpaRepository
    -0.91
    POSITIVE LOGITS
     license
    0.78
     License
    0.75
    License
    0.66
    license
    0.64
     licenses
    0.60
     LICENSE
    0.60
     licensed
    0.55
     licensing
    0.55
     copyright
    0.54
     software
    0.53
    Activations Density 1.525%

    No Known Activations