© 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. 19492
    Prev
    Next
    INDEX
    Explanations

    questions and discussions about programming or coding concepts

    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
     kasarigan
    -0.67
     AssemblyTitle
    -0.61
    yntaxException
    -0.59
     ModelExpression
    -0.57
     FetchType
    -0.54
    ContentAlignment
    -0.51
    MessageTagHelper
    -0.51
    nu
    -0.50
    gnore
    -0.50
    inine
    -0.50
    POSITIVE LOGITS
    Personendaten
    0.62
    rungsseite
    0.60
     negroes
    0.55
     étoit
    0.54
    GEBURTSDATUM
    0.52
     vorticity
    0.50
     rispetto
    0.50
     niega
    0.50
    glGen
    0.49
     themſelves
    0.49
    Activations Density 0.249%

    No Known Activations