© 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. 18-RES-MATRYOSHKA-DC
    7. 13
    Prev
    Next
    INDEX
    Explanations

    statistical data with numerical values

    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.18.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.18.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
    Portale
    -0.94
    GEBURTSDATUM
    -0.85
    setVerticalGroup
    -0.84
    ItemBackground
    -0.83
     SafeMath
    -0.81
    Rhestr
    -0.78
    SourceChecksum
    -0.76
     مُعرِّف
    -0.74
    webElement
    -0.73
    Datuak
    -0.72
    POSITIVE LOGITS
    1
    0.93
    3
    0.90
    2
    0.90
    4
    0.88
     
    0.85
    7
    0.82
    8
    0.82
    5
    0.82
    6
    0.82
    9
    0.81
    Activations Density 11.442%

    No Known Activations