© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12450
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual, particularly mentioning the name or identifying details of Mel or Melvin

    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
    mel
    -1.27
    melt
    -0.90
     melting
    -0.90
     melt
    -0.82
    melting
    -0.76
     melted
    -0.67
     melts
    -0.65
    mels
    -0.61
    Melting
    -0.59
     Melting
    -0.59
    POSITIVE LOGITS
     Mel
    2.44
    Mel
    2.34
    InjectAttribute
    0.90
     melatonin
    0.90
    KommentareTeilen
    0.88
    tvguidetime
    0.87
    TemporalType
    0.80
    principalColumn
    0.78
     GenerationType
    0.77
    ParallelGroup
    0.77
    Activations Density 0.001%

    No Known Activations