© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11309
    Prev
    Next
    INDEX
    Explanations

    instances of the word "flip" and its variations

    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
     Barth
    -0.69
    erdan
    -0.66
     Brandt
    -0.63
     tratti
    -0.63
     carottes
    -0.62
    MLLoader
    -0.62
    awtextra
    -0.62
     Cordero
    -0.60
     nubes
    -0.60
    ňov
    -0.59
    POSITIVE LOGITS
     flip
    1.80
     flips
    1.73
     flipping
    1.57
    flip
    1.53
     flipped
    1.53
     Flip
    1.52
    Flip
    1.44
     Fli
    1.41
    Fli
    1.32
    FLIP
    1.21
    Activations Density 0.007%

    No Known Activations