© 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. 2-RES-MATRYOSHKA-DC
    7. 4748
    Prev
    Next
    INDEX
    Explanations

    mentions of forgetting or memory loss

    oai_token-act-pair · gpt-4.1-nano
    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
     snippetHide
    -0.88
    OGND
    -0.78
    PreferredItem
    -0.74
    TintMode
    -0.68
    ByVersion
    -0.66
     estimés
    -0.65
     lenker
    -0.64
     nakalista
    -0.64
     <=",
    -0.64
    makeText
    -0.63
    POSITIVE LOGITS
     forget
    3.53
     forgets
    3.06
     forgetting
    3.00
    forget
    2.95
     forgot
    2.88
     forgotten
    2.80
     Forget
    2.78
     FORGET
    2.72
    Forget
    2.61
    forgotten
    2.36
    Activations Density 0.004%

    No Known Activations