© 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. 13982
    Prev
    Next
    INDEX
    Explanations

    the probability of system failure or conditions indicating a low probability of successful photon generation

    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
     grounds
    -1.00
    grounds
    -0.94
     Grounds
    -0.89
     earths
    -0.67
     Earth
    -0.66
    #+#
    -0.64
     EARTH
    -0.64
     earth
    -0.63
     ISNI
    -0.63
    <bos>
    -0.62
    POSITIVE LOGITS
     propOrder
    0.55
     للمعارف
    0.54
    illance
    0.53
    eraard
    0.51
    HOM
    0.50
    ことができました
    0.50
    ėjo
    0.49
     Beleuchtung
    0.48
    getahuan
    0.47
     mußte
    0.47
    Activations Density 0.003%

    No Known Activations