© 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. 954
    Prev
    Next
    INDEX
    Explanations

    cooking recipes

    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
     Bahkan
    -0.52
     manufactured
    -0.51
     custom
    -0.50
     مرئيه
    -0.47
    manufactured
    -0.47
     constructed
    -0.47
    ])->
    -0.46
     AppColors
    -0.44
     [][]
    -0.44
    diğinde
    -0.44
    POSITIVE LOGITS
     coarsely
    0.76
    Personendaten
    0.68
    IVEREF
    0.68
     vivement
    0.66
    momix
    0.65
     excès
    0.64
    KURZBESCHREIBUNG
    0.63
     thinly
    0.63
     paralelo
    0.63
     ingrédients
    0.62
    Activations Density 0.226%

    No Known Activations