© 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. 3-RES-MATRYOSHKA-DC
    7. 3068
    Prev
    Next
    INDEX
    Explanations

    mentions of springs or spring-loaded mechanisms

    oai_token-act-pair · gemini-2.0-flash
    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
    GEBURTSDATUM
    -0.97
    脚注の使い方
    -0.96
    PerformLayout
    -0.84
     Normdatei
    -0.82
    μως
    -0.80
    ymce
    -0.80
    Personendaten
    -0.76
     تانيه
    -0.75
    Vidite
    -0.75
    InputBorder
    -0.74
    POSITIVE LOGITS
     spring
    3.36
     Spring
    3.23
    Spring
    3.16
    spring
    3.13
     SPRING
    2.94
     springs
    2.89
    SPRING
    2.77
    springs
    2.44
     Springs
    2.38
     SPRINGS
    2.22
    Activations Density 0.040%

    No Known Activations