© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19587
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation and engagement with content

    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
    ResumeLayout
    -0.60
    acty
    -0.48
    чита
    -0.47
    </tfoot>
    -0.45
    amo
    -0.44
    áce
    -0.44
    navigationItem
    -0.44
    Życiorys
    -0.43
    resolver
    -0.42
     Abou
    -0.42
    POSITIVE LOGITS
    ItemBackground
    0.84
     SIMBAD
    0.83
    Personendaten
    0.81
    хьтан
    0.78
     ExecuteAsync
    0.73
    AddTagHelper
    0.73
    elemField
    0.72
    ✨:
    0.72
    contentLoaded
    0.69
     Lightboxes
    0.68
    Activations Density 0.011%

    No Known Activations