© 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. 12684
    Prev
    Next
    INDEX
    Explanations

    mentions of the purpose or intended use of something

    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
     meaning
    -0.78
     intention
    -0.73
     purposes
    -0.69
     intent
    -0.61
     intentions
    -0.59
    meaning
    -0.57
     Meaning
    -0.57
    ELINES
    -0.55
    ?—
    -0.52
    DIN
    -0.51
    POSITIVE LOGITS
     PURPOSE
    1.80
    PURPOSE
    1.74
    Purpose
    1.42
     Purpose
    0.90
    ⓧ
    0.77
    PerformLayout
    0.72
     AssemblyCulture
    0.68
    영어
    0.65
    ρους
    0.65
    ########.
    0.64
    Activations Density 0.001%

    No Known Activations