© 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. 32165
    Prev
    Next
    INDEX
    Explanations

    references to legal trials

    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
    rungsseite
    -0.92
    Pranala
    -0.57
     momenti
    -0.57
    verwijspagina
    -0.55
    ̴
    -0.53
    ướ
    -0.52
     kasarigan
    -0.51
    uronic
    -0.51
    ciech
    -0.50
    TextSpan
    -0.50
    POSITIVE LOGITS
     Normdatei
    0.72
     AssemblyCompany
    0.67
     الحره
    0.65
    stdbool
    0.64
     hanem
    0.63
    sizeCache
    0.63
     ControllerBase
    0.59
     OnInit
    0.59
    DrawerLayout
    0.59
    rceil
    0.58
    Activations Density 0.014%

    No Known Activations