© 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. 18-RES-MATRYOSHKA-DC
    7. 816
    Prev
    Next
    INDEX
    Explanations

    the word "source", especially when followed by "control"

    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.18.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.18.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
    AlterField
    -0.49
    <h2>
    -0.44
    ricane
    -0.43
     Audiodateien
    -0.42
    ştir
    -0.41
    Trish
    -0.41
     numberOfRows
    -0.41
    кнуть
    -0.40
    thyl
    -0.40
    <h3>
    -0.40
    POSITIVE LOGITS
     SOURCE
    1.22
     Sources
    1.21
     sources
    1.19
     source
    1.13
    Sources
    1.12
    sources
    1.10
    源
    1.03
     Source
    1.02
    Fuentes
    1.02
     源
    0.98
    Activations Density 0.497%

    No Known Activations