© 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. 15420
    Prev
    Next
    INDEX
    Explanations

    terms related to data processing and statistical modeling techniques

    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
     actionMode
    -0.49
    #+#
    -0.47
    EXTERN
    -0.46
     مواليد
    -0.44
    DrawerLayout
    -0.44
    enterOuterAlt
    -0.43
    Edm
    -0.43
     كمان
    -0.42
     مصرى
    -0.41
    DotNetBar
    -0.41
    POSITIVE LOGITS
    gaver
    0.63
    jsonwebtoken
    0.62
    ingdon
    0.60
     الحره
    0.58
    EndContext
    0.56
    adeloupe
    0.56
    ofag
    0.56
     Uncategorized
    0.55
    الإنجليزية
    0.54
     ioutil
    0.54
    Activations Density 0.047%

    No Known Activations