© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 46067
    Prev
    Next
    INDEX
    Explanations

    free

    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
     free
    -1.03
    free
    -1.02
     Free
    -0.91
    Free
    -0.91
    FREE
    -0.77
     FREE
    -0.75
    frees
    -0.72
     freely
    -0.63
    Gratis
    -0.63
     kostenlosen
    -0.63
    POSITIVE LOGITS
     quarries
    0.54
     idols
    0.54
     groves
    0.53
     popu
    0.52
     tresses
    0.51
    ChildScrollView
    0.49
     gums
    0.49
    èdia
    0.49
     grove
    0.49
     tombs
    0.49
    Activations Density 0.009%

    No Known Activations