© 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. 18-RES-MATRYOSHKA-DC
    7. 1223
    Prev
    Next
    INDEX
    Explanations

    technical documents and abstracts, particularly the start of a section or paragraph that describes the intention of the work.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    Autoritní
    -0.68
    LookAnd
    -0.63
     katanya
    -0.52
     resourceCulture
    -0.47
    angal
    -0.46
     adipis
    -0.45
    منابع
    -0.45
    lox
    -0.44
    abilirsiniz
    -0.44
     autorytatywna
    -0.44
    POSITIVE LOGITS
     briefly
    1.34
     discuss
    1.34
     discussing
    1.30
     discusses
    1.30
     discussion
    1.20
     brief
    1.10
     overview
    1.09
     Discus
    1.08
     Discuss
    1.05
     membahas
    1.03
    Activations Density 1.313%

    No Known Activations