© 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. 15337
    Prev
    Next
    INDEX
    Explanations

    settings related to core configurations and specifications

    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
     חיצוניים
    -0.52
    门
    -0.47
    struts
    -0.45
    ficult
    -0.45
    请问
    -0.43
    Core
    -0.43
     individuales
    -0.43
    ่อย
    -0.42
    門
    -0.42
    utils
    -0.41
    POSITIVE LOGITS
     cores
    2.86
     Cores
    2.30
    cores
    1.88
    Cores
    1.88
    tvguidetime
    0.82
    InstrumentedTest
    0.82
    IndentedString
    0.76
     disambiguazione
    0.75
     Normdatei
    0.75
    PyExc
    0.74
    Activations Density 0.002%

    No Known Activations