© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1383
    Prev
    Next
    INDEX
    Explanations

    passages describing experimental conditions, including concentrations of reagents and dilutions

    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
    ########.
    -0.82
    createServer
    -0.50
     groupBox
    -0.50
     uVar
    -0.47
     وتسجيلات
    -0.46
     lap
    -0.44
    AnimationsModule
    -0.44
    ENSA
    -0.44
    etu
    -0.43
    knię
    -0.43
    POSITIVE LOGITS
     concentration
    1.90
     concentrations
    1.73
     Concentration
    1.71
    concentration
    1.66
    Concentration
    1.59
     Concentrations
    1.59
     CONCENT
    1.52
    concentr
    1.41
    Concentr
    1.39
     Konzentration
    1.30
    Activations Density 0.913%

    No Known Activations