© 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. 28501
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant achievements or findings in a historical or scientific context

    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
    saraba
    -0.65
    GENERATED
    -0.59
     dago
    -0.57
    ValueGeneration
    -0.56
     Efq
    -0.56
     fotográfica
    -0.54
     jsPsych
    -0.54
     iſt
    -0.54
    autoreleasepool
    -0.53
     marqués
    -0.53
    POSITIVE LOGITS
     bowiem
    0.66
     Réponses
    0.63
    @[+][
    0.63
     totiž
    0.58
    NewUrlParser
    0.57
     infatti
    0.55
     nämlich
    0.55
    Viitteet
    0.52
    tagHelperRunner
    0.50
    meanor
    0.50
    Activations Density 0.459%

    No Known Activations