© 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. 22-RES-MATRYOSHKA-DC
    7. 2880
    Prev
    Next
    INDEX
    Explanations

    words related to favors, obtaining objects, and general helpfulness

    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.22.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.22.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
     anledning
    -0.56
    queryInterface
    -0.55
    AutoScaleMode
    -0.53
    gameserver
    -0.52
    GTCX
    -0.51
    SBATCH
    -0.51
    Diweddarwch
    -0.51
    lesias
    -0.50
    tagext
    -0.50
    elemField
    -0.49
    POSITIVE LOGITS
     food
    0.84
     drinks
    0.81
     dinner
    0.80
     supper
    0.80
     snacks
    0.79
     coffee
    0.79
     lunch
    0.78
     breakfast
    0.76
     refreshments
    0.73
     cigarettes
    0.71
    Activations Density 0.366%

    No Known Activations