© 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. 15076
    Prev
    Next
    INDEX
    Explanations

    references to unspecified or unrecognized technical or system components

    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
     برانيه
    -0.52
    NewUrlParser
    -0.50
     likely
    -0.46
     TestBed
    -0.46
    Carrying
    -0.46
    ManagedBean
    -0.46
     pair
    -0.45
    ļas
    -0.45
     Anlass
    -0.45
    leistungs
    -0.44
    POSITIVE LOGITS
    Unknown
    2.36
    UNKNOWN
    1.31
     Unknown
    1.24
    Unk
    1.14
    AndEndTag
    1.05
     UNKNOWN
    0.87
    ########.
    0.87
     EconPapers
    0.87
     defaultstate
    0.87
    unknown
    0.86
    Activations Density 0.002%

    No Known Activations