© 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. 22984
    Prev
    Next
    INDEX
    Explanations

    mathematical relationships, specifically those related to factors and multiples

    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
    Попис
    -0.89
     يتيمه
    -0.81
    DeleteBehavior
    -0.79
     EconPapers
    -0.79
    afficheront
    -0.77
     disambiguazione
    -0.77
    WithIOException
    -0.75
    tagHelperRunner
    -0.75
     appelez
    -0.75
     oprot
    -0.72
    POSITIVE LOGITS
    nitzer
    0.47
     Mar
    0.46
    osexual
    0.46
    لمين
    0.45
     Mays
    0.44
    OrNil
    0.42
     Clark
    0.42
    ztal
    0.42
    rova
    0.41
     Parrish
    0.41
    Activations Density 0.249%

    No Known Activations