© 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. 15360
    Prev
    Next
    INDEX
    Explanations

    references to commitments or assurances that have been made or fulfilled

    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
    发表于
    -0.69
    ьаж
    -0.67
    ThroughAttribute
    -0.64
     Rekord
    -0.64
    комен
    -0.63
     <<<<<<<<<<<<<<
    -0.62
    ">//
    -0.62
    Географи
    -0.60
     estekak
    -0.59
    CPtr
    -0.59
    POSITIVE LOGITS
     promised
    2.39
     Promised
    1.36
     pledged
    0.81
     owed
    0.65
     lost
    0.60
     prome
    0.56
    bcryptjs
    0.54
     required
    0.51
     vowed
    0.51
     per
    0.50
    Activations Density 0.001%

    No Known Activations