© 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. 23762
    Prev
    Next
    INDEX
    Explanations

    characters and their relationships within a fantasy or story-like 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
    babu
    -0.48
    je
    -0.43
    ild
    -0.41
    size
    -0.40
    es
    -0.40
    жд
    -0.40
    log
    -0.40
    led
    -0.39
    bey
    -0.39
    si
    -0.39
    POSITIVE LOGITS
    Autoritní
    1.00
    AddTagHelper
    0.98
    extAlignment
    0.98
    GEBURTSDATUM
    0.97
     myſelf
    0.93
    
    0.91
     समीक्षाओं
    0.90
    клопе
    0.90
     ExecuteAsync
    0.89
    AutoScale
    0.88
    Activations Density 0.141%

    No Known Activations