© 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. 1145
    Prev
    Next
    INDEX
    Explanations

    scientific language about resonances, nanoparticles, and spectral analysis

    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
     sabato
    -0.52
    schedulers
    -0.50
     Tante
    -0.49
    խ
    -0.49
     intptr
    -0.48
    /******/
    -0.48
    تماد
    -0.48
    reportWebVitals
    -0.48
     OFDb
    -0.47
     Suff
    -0.47
    POSITIVE LOGITS
     peaks
    1.30
     peak
    1.30
    peak
    1.16
     Peaks
    1.13
    Peak
    1.12
     Peak
    1.11
    peaks
    1.05
     PEAK
    0.98
     peaking
    0.95
    ピーク
    0.92
    Activations Density 1.212%

    No Known Activations