© 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. 373
    Prev
    Next
    INDEX
    Explanations

    the start and end of mathematical and scientific expressions including the word "model" and the word "matter"

    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
     propOrder
    -0.68
     useParams
    -0.56
     apparente
    -0.54
    Measured
    -0.53
    Cous
    -0.53
    eriks
    -0.51
    jmniej
    -0.50
    ệc
    -0.50
     cadence
    -0.50
    󠁢
    -0.50
    POSITIVE LOGITS
    aarrggbb
    0.60
     dense
    0.59
     gas
    0.59
    Feedback
    0.57
    dense
    0.56
    WriteTagHelper
    0.56
     forming
    0.55
     Feedback
    0.54
    Tikang
    0.54
     acc
    0.53
    Activations Density 0.750%

    No Known Activations