© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4032
    Prev
    Next
    INDEX
    Explanations

    terms related to compositions and structures in various contexts

    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
    ьаж
    -1.05
    IsPostBack
    -1.05
     متعلقه
    -1.02
    hadur
    -0.98
    GEBURTSDATUM
    -0.95
    Παραπομπές
    -0.89
    expandindo
    -0.89
    GenerationType
    -0.88
    alnız
    -0.88
    RunWith
    -0.87
    POSITIVE LOGITS
    Compos
    1.52
     compositions
    1.41
     Compose
    1.39
     Composition
    1.38
     compos
    1.36
     Compos
    1.36
     composed
    1.31
     COMPOS
    1.29
     Composed
    1.25
     composition
    1.24
    Activations Density 0.034%

    No Known Activations