© 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. 11929
    Prev
    Next
    INDEX
    Explanations

    numerical values or calculations

    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
     lenker
    -0.66
     Roskov
    -0.63
    ագրություններ
    -0.59
    TintMode
    -0.58
    BURG
    -0.55
    LabelTagHelper
    -0.54
    UrlResolution
    -0.52
     становника
    -0.49
    isburg
    -0.49
    цездатний
    -0.48
    POSITIVE LOGITS
    CreateModel
    0.69
     internazionale
    0.67
     internazionali
    0.58
     AssemblyCompany
    0.56
     aéri
    0.54
     Económica
    0.53
     userModel
    0.53
     Timp
    0.52
     internacional
    0.52
     internationaux
    0.52
    Activations Density 0.060%

    No Known Activations