© 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. 3662
    Prev
    Next
    INDEX
    Explanations

    phrases related to expected features and performance in a system or product 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
    出版年
    -0.52
    anger
    -0.49
     Tonight
    -0.45
    orcid
    -0.44
     uska
    -0.43
    brainly
    -0.42
     express
    -0.41
     mostrarán
    -0.41
    да
    -0.40
    ́c
    -0.40
    POSITIVE LOGITS
     typical
    0.86
    HideFlags
    0.80
     >=",
    0.77
    typical
    0.75
     typique
    0.72
    Typical
    0.70
     típico
    0.70
     Typical
    0.68
     típica
    0.68
    RenderAtEndOf
    0.68
    Activations Density 0.523%

    No Known Activations