© 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. 22200
    Prev
    Next
    INDEX
    Explanations

    syntax structures that include brackets or parentheses

    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
     preventivo
    -0.57
     viewDidLoad
    -0.56
     saluti
    -0.53
    LookAnd
    -0.52
     extremos
    -0.50
    InitVars
    -0.50
    Havolalar
    -0.49
     agrí
    -0.49
     linkovi
    -0.49
    혁
    -0.48
    POSITIVE LOGITS
    󠁿
    0.57
    vdots
    0.53
    SequentialGroup
    0.53
    ్రామ
    0.53
     Boas
    0.52
    FromNib
    0.52
     Sleeper
    0.52
    XmlAccessType
    0.50
    省市镇
    0.49
    Rhestr
    0.48
    Activations Density 0.168%

    No Known Activations