© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 11837
    Prev
    Next
    INDEX
    Explanations

    emotional intensity related to urgency and pathos

    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
    parsedMessage
    -0.71
    IntoConstraints
    -0.65
     Huguen
    -0.64
     CreateTagHelper
    -0.64
    DeleteBehavior
    -0.62
     Langmuir
    -0.62
    ResumeLayout
    -0.59
     Mahabhar
    -0.59
    دانشنامهٔ
    -0.58
    abestanden
    -0.55
    POSITIVE LOGITS
     sour
    1.13
     Gloria
    0.82
    sour
    0.79
     Sour
    0.78
     få
    0.75
    licant
    0.72
    oren
    0.72
    Gloria
    0.69
     fått
    0.66
     fået
    0.66
    Activations Density 0.002%

    No Known Activations