© 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. 26769
    Prev
    Next
    INDEX
    Explanations

    numerical values and quantities related to items or events

    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
     myſelf
    -0.88
     Majefty
    -0.87
     himſelf
    -0.86
     oprot
    -0.85
     itſelf
    -0.84
    ^(@)
    -0.81
     raiſ
    -0.80
     poffe
    -0.79
     Efq
    -0.78
    Personensuche
    -0.76
    POSITIVE LOGITS
    出版年
    0.52
     she
    0.43
     rock
    0.39
     chi
    0.36
    новниш
    0.35
    ConverterFactory
    0.35
     pro
    0.35
     il
    0.35
     cos
    0.34
     osp
    0.34
    Activations Density 0.444%

    No Known Activations