© 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. 0-CLT-HP
    7. 94973
    Prev
    Next
    INDEX
    Explanations

    melt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Melt
    -1.30
     melt
    -1.21
    Melt
    -1.16
     Melting
    -1.13
     melting
    -1.11
     melted
    -1.00
    melt
    -1.00
     melts
    -0.92
    melting
    -0.88
     thaw
    -0.85
    POSITIVE LOGITS
    ness
    0.90
    ly
    0.61
    EndInit
    0.56
    IGENCE
    0.53
     process
    0.52
     product
    0.49
     processes
    0.48
     propri
    0.48
    NESS
    0.47
    bone
    0.47
    Activations Density 0.189%

    No Known Activations