© 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. 0-RES-MATRYOSHKA-DC
    7. 12783
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases describing positive reviews or endorsements

    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
    ItemBackground
    -0.79
     remplace
    -0.64
     متعلقه
    -0.62
    Largeur
    -0.62
    Pemer
    -0.61
    easily
    -0.59
    pahan
    -0.59
    garder
    -0.59
     Estructura
    -0.59
    Aggi
    -0.59
    POSITIVE LOGITS
    Valid
    2.61
     Valid
    1.55
    VALID
    0.66
    BeginContext
    0.60
    Validated
    0.57
    SourceChecksum
    0.57
    AndEndTag
    0.55
    celotti
    0.53
     Reliable
    0.51
    Empty
    0.50
    Activations Density 0.002%

    No Known Activations