© 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. 18-RES-MATRYOSHKA-DC
    7. 768
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to something that has already occurred or been completed

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     ISNI
    -0.56
    ėms
    -0.53
     كومونز
    -0.48
    RunAsync
    -0.48
    емых
    -0.47
     CreateTagHelper
    -0.47
    鰭
    -0.45
    marshaller
    -0.44
    asa
    -0.44
    Einzelnachweise
    -0.44
    POSITIVE LOGITS
     already
    3.91
    already
    3.61
     Already
    3.45
    Already
    3.34
     ALREADY
    3.14
    ALREADY
    2.66
     allerede
    2.59
     이미
    2.53
     redan
    2.52
     déjà
    2.44
    Activations Density 2.461%

    No Known Activations