© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15494
    Prev
    Next
    INDEX
    Explanations

    references to the quality or effectiveness of something

    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
    PSA
    -0.51
    ROIT
    -0.46
     native
    -0.45
    getProducts
    -0.44
    ivable
    -0.43
    MDL
    -0.42
    országban
    -0.42
    โลก
    -0.41
    espn
    -0.41
     enca
    -0.40
    POSITIVE LOGITS
    AnchorStyles
    1.08
    +#+#
    0.98
     архивлан
    0.93
    awtextra
    0.92
    LookAnd
    0.88
    Geplaatst
    0.86
    MessageTagHelper
    0.84
    UnusedPrivate
    0.84
    RegistryLite
    0.82
    ########.
    0.82
    Activations Density 0.152%

    No Known Activations