© 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. 671
    Prev
    Next
    INDEX
    Explanations

    text where someone is referencing bicycle maintenance and repair

    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
     playwright
    -0.56
     Playhouse
    -0.56
    carat
    -0.52
     jugado
    -0.52
    kháu
    -0.51
    EditorBrowsable
    -0.50
     ivi
    -0.49
     Theater
    -0.49
     theatre
    -0.48
     Egyp
    -0.48
    POSITIVE LOGITS
     bike
    1.57
     riders
    1.53
     riding
    1.49
     rider
    1.47
     bikes
    1.38
     Bike
    1.32
     ride
    1.31
     ridden
    1.25
    Bike
    1.24
    bike
    1.23
    Activations Density 0.384%

    No Known Activations