© 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. 1834
    Prev
    Next
    INDEX
    Explanations

    mentions of chemical properties and ppm values in technical writing

    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
    rungsseite
    -0.57
     lenker
    -0.56
     fhort
    -0.56
    ThroughAttribute
    -0.55
    pageY
    -0.55
    TagName
    -0.54
     adher
    -0.52
     TAMBIÉN
    -0.52
    UserScript
    -0.51
    bade
    -0.51
    POSITIVE LOGITS
    `;
    0.58
     Himo
    0.54
    modb
    0.52
    Hz
    0.49
    diğini
    0.49
    ")));
    0.49
    eraard
    0.48
     assignable
    0.48
     overlapped
    0.48
    wardship
    0.47
    Activations Density 0.114%

    No Known Activations