© 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. 4-CLT-HP
    7. 4734
    Prev
    Next
    INDEX
    Explanations

    entertain

    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
     Allociné
    -0.46
    FormsModule
    -0.43
    nical
    -0.42
     Administrativna
    -0.42
     gehör
    -0.42
     sahiptir
    -0.42
    fohl
    -0.41
    Kare
    -0.40
     sekali
    -0.39
    nonatomic
    -0.38
    POSITIVE LOGITS
     onOptions
    0.82
    enterOuterAlt
    0.66
    :✨
    0.64
    /**
    0.63
     ioutil
    0.60
    unknownFields
    0.59
     يتيمه
    0.59
    thoughts
    0.59
    ValueGenerated
    0.57
     the
    0.57
    Activations Density 0.022%

    No Known Activations