© 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. 12-RES-MATRYOSHKA-DC
    7. 18479
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     समीक्षक
    -0.65
     Lang
    -0.65
     صوتيه
    -0.65
     незавершена
    -0.63
    UserScript
    -0.62
    WebElementEntity
    -0.59
    MessageTagHelper
    -0.59
    IonicModule
    -0.58
     FontWeight
    -0.56
     متعلقه
    -0.56
    POSITIVE LOGITS
     оригіналу
    0.68
    forRoot
    0.60
    StreetMap
    0.57
     lenker
    0.56
     anteced
    0.54
     escapar
    0.53
    انيف
    0.53
    Становништво
    0.52
    mtrl
    0.52
     Rasp
    0.52
    Activations Density 0.087%

    No Known Activations