© 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. 320
    Prev
    Next
    INDEX
    Explanations

    capitalized names and/or initials, often followed by a number

    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
     présidenti
    -0.66
     Theſe
    -0.60
     dieux
    -0.60
    déric
    -0.59
    cemment
    -0.59
    avice
    -0.57
    knecht
    -0.57
    zenberg
    -0.56
     chrétiens
    -0.56
     resourceCulture
    -0.55
    POSITIVE LOGITS
     actionMode
    0.65
     "..\..\..\
    0.65
    ⓧ
    0.62
     snare
    0.62
    rá
    0.61
    бище
    0.61
     noDo
    0.60
     "..\..\
    0.60
     Wikimedijinoj
    0.60
    ocarcinoma
    0.60
    Activations Density 1.420%

    No Known Activations