© 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. 0-CLT-HP
    7. 38612
    Prev
    Next
    INDEX
    Explanations

    copyright licenses

    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
     nativity
    -1.61
    AndEndTag
    -0.93
    CopyWith
    -0.77
     BoxFit
    -0.75
    RegressionTest
    -0.74
    ytale
    -0.72
    CROSSTALK
    -0.68
    PerformLayout
    -0.68
     AppComponent
    -0.66
    StructEnd
    -0.66
    POSITIVE LOGITS
     houſe
    0.44
     pleaſure
    0.41
    IsContent
    0.40
    ală
    0.40
     ſche
    0.40
     Inſ
    0.39
     purpoſe
    0.39
    Presence
    0.39
     laſt
    0.37
    Bye
    0.37
    Activations Density 0.112%

    No Known Activations