© 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. 21699
    Prev
    Next
    INDEX
    Explanations

    color-related terms and their usage in visual representations

    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
    TING
    -0.59
    ecks
    -0.53
     wood
    -0.51
    WEBPACK
    -0.51
    dees
    -0.51
    ckeye
    -0.51
    daille
    -0.51
    awtextra
    -0.51
    alpha
    -0.50
     lou
    -0.50
    POSITIVE LOGITS
     virtuales
    0.73
     digitais
    0.69
     onPostExecute
    0.66
    testens
    0.66
    Życiorys
    0.64
     automatiques
    0.63
     artificiales
    0.62
     endwhile
    0.60
     personalizadas
    0.60
     conozco
    0.58
    Activations Density 0.012%

    No Known Activations