© 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. 1-RES-MATRYOSHKA-DC
    7. 773
    Prev
    Next
    INDEX
    Explanations

    instances of the word "signed" in various contexts

    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
     alerts
    -0.75
     alert
    -0.74
     Alert
    -0.68
     Alerts
    -0.66
     pulses
    -0.64
     messengers
    -0.63
    alert
    -0.63
     ComVisible
    -0.61
     notifications
    -0.60
    WriteAttribute
    -0.59
    POSITIVE LOGITS
     signed
    4.06
     sign
    3.95
     signing
    3.70
     Sign
    3.55
     Signed
    3.55
    signed
    3.47
     SIGN
    3.36
     Signing
    3.36
    Sign
    3.33
    Signed
    3.28
    Activations Density 0.297%

    No Known Activations