© 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. 26508
    Prev
    Next
    INDEX
    Explanations

    programming commands and functions

    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
    くれた
    -0.46
     elsewhere
    -0.45
    caten
    -0.45
    
    -0.44
    modb
    -0.43
    定義
    -0.42
     جایی
    -0.42
    ?:
    -0.42
     SqlCommand
    -0.41
    richTextPanel
    -0.41
    POSITIVE LOGITS
     contextLoads
    0.91
     оригіналу
    0.82
    󠁿
    0.76
    GraphicsUnit
    0.73
    InstrumentedTest
    0.72
    liothèque
    0.69
    parametrize
    0.69
    istoitu
    0.69
    Enllaces
    0.69
    CloseHandle
    0.69
    Activations Density 0.059%

    No Known Activations