© 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. 14141
    Prev
    Next
    INDEX
    Explanations

    responses indicating unusual symbols or formatting artifacts

    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
    illeur
    -0.60
    pandora
    -0.58
     digitais
    -0.56
     tentative
    -0.55
     Hast
    -0.54
     blackmail
    -0.54
    León
    -0.54
     tradicionais
    -0.54
    цездатний
    -0.53
    PutMapping
    -0.52
    POSITIVE LOGITS
    .--
    1.90
    !--
    0.84
    Vidite
    0.69
    oa̍t
    0.63
    omány
    0.60
    )/(
    0.58
    BoxLayout
    0.57
    /−
    0.57
     оригіналу
    0.56
    ifikant
    0.56
    Activations Density 0.000%

    No Known Activations