© 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. 15087
    Prev
    Next
    INDEX
    Explanations

    the presence of specific types of high-conductance, mathematical or technical terms related to electronics and circuit theory

    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
    ances
    -1.52
    ANCES
    -0.93
    anced
    -0.86
    ancer
    -0.72
    //
    -0.72
    出版年
    -0.70
     Normdatei
    -0.59
    ANCED
    -0.59
    extAlignment
    -0.58
    éez
    -0.58
    POSITIVE LOGITS
    ance
    1.51
    лерея
    0.59
     Socrates
    0.56
     Tacitus
    0.55
     Bellow
    0.54
     Mulher
    0.53
     blancs
    0.53
     villains
    0.51
    لوم
    0.51
    éges
    0.51
    Activations Density 0.002%

    No Known Activations