© 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. 2-RES-MATRYOSHKA-DC
    7. 6443
    Prev
    Next
    INDEX
    Explanations

    references to the name Mel or its variations

    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
    Tus
    -0.59
     Tus
    -0.56
     Gautier
    -0.56
    strokeStyle
    -0.56
     Araujo
    -0.54
    jupiter
    -0.53
     PropTypes
    -0.53
     Bally
    -0.53
    گون
    -0.52
    elasticsearch
    -0.52
    POSITIVE LOGITS
    mel
    3.33
     Mel
    3.05
    Mel
    2.98
     mel
    2.91
     MEL
    2.75
    MEL
    2.72
     melt
    2.28
    melt
    2.23
     melts
    2.14
     melted
    2.13
    Activations Density 0.019%

    No Known Activations