© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4794
    Prev
    Next
    INDEX
    Explanations

    occurrences of timestamps and identifiers in the context of data queries

    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
    EqualsAnd
    -0.68
    jší
    -0.67
    batore
    -0.62
     otomatig
    -0.62
    AxisAlignment
    -0.60
     PriorityQueue
    -0.59
    ArgsConstructor
    -0.58
    RunAsync
    -0.58
     SDLK
    -0.58
    Ƚ
    -0.58
    POSITIVE LOGITS
    GEBURTSDATUM
    0.60
    GeoNames
    0.56
     szóci
    0.49
    ahal
    0.48
    WING
    0.48
     verf
    0.47
     disambiguazione
    0.47
     Wicidata
    0.46
    minar
    0.46
     elé
    0.46
    Activations Density 0.018%

    No Known Activations