© 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. 176
    Prev
    Next
    INDEX
    Explanations

    technical terms from scientific reports involving measurement, chemical properties, or quantities

    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
    SpringBootTest
    -0.58
    artigen
    -0.53
    posedge
    -0.51
    :+:
    -0.51
    UEZ
    -0.50
     fevere
    -0.50
    isce
    -0.48
    ąp
    -0.48
    thand
    -0.47
    artige
    -0.47
    POSITIVE LOGITS
     difference
    0.82
     ratio
    0.80
     determination
    0.72
     differences
    0.70
    difference
    0.70
     variation
    0.69
     profile
    0.69
     estimation
    0.68
     range
    0.67
     ratios
    0.67
    Activations Density 4.013%

    No Known Activations