© 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. 2209
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables related to probability or statistical measures

    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
     JpaRepository
    -0.75
    ArgsConstructor
    -0.60
    Glej
    -0.60
     CreateTagHelper
    -0.55
    UnitTesting
    -0.55
     ujednoznacz
    -0.53
    ChildScrollView
    -0.51
    TintMode
    -0.48
    Erreferentziak
    -0.48
     Accesat
    -0.48
    POSITIVE LOGITS
    UnknownFieldSet
    0.64
     تانيه
    0.60
    
    0.56
    ngdoc
    0.53
    клопе
    0.52
     voulons
    0.51
    الإنجليزية
    0.51
    ctuation
    0.48
    rungsseite
    0.48
    straints
    0.48
    Activations Density 0.999%

    No Known Activations