© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11477
    Prev
    Next
    INDEX
    Explanations

    the word "forget" and related words

    oai_token-act-pair · gemini-2.0-flash

    forget

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     forget
    -2.08
     forgets
    -1.89
     forgetting
    -1.87
     forgot
    -1.77
    forget
    -1.73
     forgotten
    -1.62
     Forget
    -1.59
     FORGET
    -1.52
    Forget
    -1.48
     olvid
    -1.43
    POSITIVE LOGITS
     chré
    0.52
     Arrondissement
    0.50
     fören
    0.49
    InSection
    0.47
    hup
    0.47
     épar
    0.47
     Nacionales
    0.47
    dom
    0.46
    miar
    0.46
     souff
    0.46
    Activations Density 10.544%

    No Known Activations