© 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. 3-RES-MATRYOSHKA-DC
    7. 2999
    Prev
    Next
    INDEX
    Explanations

    words or names starting "Fer"

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clarence
    -0.73
    AddTagHelper
    -0.67
     nawr
    -0.67
    Clarence
    -0.65
     himo
    -0.63
    évaluateur
    -0.61
    //
    -0.61
     Oru
    -0.61
    CharStream
    -0.61
     Kna
    -0.60
    POSITIVE LOGITS
     Fer
    3.03
    Fer
    3.03
    fer
    2.91
     fer
    2.81
    FER
    2.42
     FER
    2.28
     FERR
    1.67
    ferm
    1.61
     FERT
    1.61
     Фер
    1.60
    Activations Density 0.025%

    No Known Activations