© 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. 15461
    Prev
    Next
    INDEX
    Explanations

    mathematical functions related to the cosine and sine

    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
    FieldNumber
    -1.03
     pleaſure
    -0.99
    openzeppelin
    -0.96
    IsContent
    -0.92
     defaultstate
    -0.87
     faſt
    -0.86
     itſelf
    -0.85
     ſtre
    -0.82
     Vögel
    -0.82
     Theſe
    -0.81
    POSITIVE LOGITS
     Cos
    1.43
     cos
    1.38
    Cos
    1.37
    cos
    1.36
     COS
    1.11
     cosine
    1.09
     Costello
    1.07
    COS
    1.06
     Cosby
    0.95
     Kos
    0.89
    Activations Density 0.010%

    No Known Activations