© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45971
    Prev
    Next
    INDEX
    Explanations

    thawing

    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
     thawed
    -0.87
    Frozen
    -0.85
     Frozen
    -0.82
     defrost
    -0.80
     froze
    -0.78
    frozen
    -0.78
     frozen
    -0.77
     thawing
    -0.77
    Freeze
    -0.75
     مشين
    -0.75
    POSITIVE LOGITS
    AutoField
    0.50
    ekse
    0.47
     Weltkrieg
    0.47
     gynhyrchwyd
    0.47
     hitch
    0.46
     AssemblyTitle
    0.45
    homonymie
    0.44
    akte
    0.43
     weakly
    0.43
    atterson
    0.43
    Activations Density 0.010%

    No Known Activations