© 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. 11047
    Prev
    Next
    INDEX
    Explanations

    references to particularly negative or harmful events or qualities

    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
     horror
    -0.82
    horror
    -0.76
     Horror
    -0.73
    Horror
    -0.68
    RefNanny
    -0.63
    vertx
    -0.57
    Hor
    -0.57
     succes
    -0.56
     grotes
    -0.54
     disgust
    -0.53
    POSITIVE LOGITS
     terrible
    2.06
    terrible
    1.95
     Terrible
    1.67
     awful
    1.45
    Terrible
    1.44
    awful
    1.02
     horrible
    1.02
     terribly
    0.91
    Awful
    0.82
     AssemblyVersion
    0.80
    Activations Density 0.002%

    No Known Activations