© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93462
    Prev
    Next
    INDEX
    Explanations

    drinks

    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
     juice
    -0.48
     jorden
    -0.47
     len
    -0.45
    섬
    -0.45
     milk
    -0.44
     dentaire
    -0.44
     fiber
    -0.43
    ppure
    -0.42
     fibre
    -0.42
    CSharp
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.68
    medriver
    0.68
     myſelf
    0.67
    zzleHttp
    0.67
    setVerticalGroup
    0.66
     itſelf
    0.65
    WaitGroup
    0.65
     cruises
    0.63
     Meille
    0.63
    }}]{
    0.62
    Activations Density 0.062%

    No Known Activations