© 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. 2699
    Prev
    Next
    INDEX
    Explanations

    the word "Fla" followed by other letters, possibly as part of a scientific name or place

    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
     Италијани
    -0.71
    DispatchToProps
    -0.57
    ༘
    -0.54
    ContentAlignment
    -0.54
     credere
    -0.53
     fieldNum
    -0.52
    NewUrlParser
    -0.51
    \[\
    -0.50
    MethodType
    -0.48
     Roskov
    -0.48
    POSITIVE LOGITS
     Fla
    1.03
    Fla
    0.86
     FL
    0.85
     fla
    0.83
     fl
    0.81
     Fl
    0.80
     Flag
    0.78
    Flg
    0.77
     flag
    0.76
    fla
    0.73
    Activations Density 0.116%

    No Known Activations