© 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. 19571
    Prev
    Next
    INDEX
    Explanations

    expressions of frequency and likelihood

    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
     chofe
    -0.63
     samot
    -0.60
     Etats
    -0.58
     organes
    -0.57
     fantasmas
    -0.56
     lå
    -0.56
    odacty
    -0.55
    Adventures
    -0.55
     rossi
    -0.54
     vola
    -0.53
    POSITIVE LOGITS
     nakalista
    0.69
     BoxDecoration
    0.65
     lenker
    0.64
     snippetHide
    0.64
    AnchorStyles
    0.63
     مرئيه
    0.60
     cherchés
    0.58
    GroupLayout
    0.57
     isComment
    0.57
     with
    0.57
    Activations Density 0.072%

    No Known Activations