© 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. 12-RES-MATRYOSHKA-DC
    7. 6353
    Prev
    Next
    INDEX
    Explanations

    instances of the word "interest" related to various contexts

    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
     Napa
    -0.69
    scriptcase
    -0.68
     Cabrera
    -0.68
    akana
    -0.67
    izop
    -0.65
    DNEY
    -0.65
    — 
    -0.64
     Dion
    -0.63
    لمانيا
    -0.62
     nélk
    -0.61
    POSITIVE LOGITS
     interest
    2.02
     Interest
    2.00
     interests
    1.96
    Interest
    1.88
     INTEREST
    1.88
    interest
    1.84
     Interests
    1.80
    INTEREST
    1.71
    interests
    1.60
    Interests
    1.60
    Activations Density 0.056%

    No Known Activations