© 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. 3016
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "GF" when it refers to growth factors

    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
    FXML
    -0.56
    inemann
    -0.56
    antd
    -0.55
     Tod
    -0.52
    رة
    -0.51
    antos
    -0.50
    skri
    -0.49
     artig
    -0.49
     Versch
    -0.47
     Ulrich
    -0.47
    POSITIVE LOGITS
    GF
    2.70
     GF
    2.22
    gf
    1.88
     gf
    1.52
    Gf
    1.09
    Carriera
    0.74
    awtextra
    0.71
    bootstrapcdn
    0.71
     Meksiku
    0.68
     Irm
    0.68
    Activations Density 0.005%

    No Known Activations