© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16728
    Prev
    Next
    INDEX
    Explanations

    terms related to music composition and creative writing

    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
     works
    -0.59
     himself
    -0.48
    Works
    -0.48
    works
    -0.47
     trabalha
    -0.45
     working
    -0.45
     work
    -0.44
    working
    -0.44
    worked
    -0.43
     él
    -0.42
    POSITIVE LOGITS
    PerformLayout
    0.74
     Италијани
    0.70
    Geplaatst
    0.70
     AssemblyCulture
    0.70
    帖最后由
    0.66
     Administrativna
    0.65
    Gute
    0.64
     podjela
    0.63
     disambiguazione
    0.62
     remonter
    0.62
    Activations Density 0.053%

    No Known Activations