© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7409
    Prev
    Next
    INDEX
    Explanations

    instances of securing or ensuring the safety or stability 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
    +#+#
    -0.78
     Safety
    -0.66
     safety
    -0.65
     препратки
    -0.64
    Safety
    -0.59
     SAFETY
    -0.58
    mybatisplus
    -0.57
     Security
    -0.56
    urity
    -0.55
    initis
    -0.54
    POSITIVE LOGITS
     secured
    2.64
     secure
    2.52
    secure
    2.34
     Secured
    2.33
     secures
    2.33
     Secure
    2.30
    secured
    2.28
     securing
    2.27
    Secure
    2.27
    Secured
    2.14
    Activations Density 0.012%

    No Known Activations