© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91833
    Prev
    Next
    INDEX
    Explanations

    religious references

    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
     esternos
    -0.67
     мәгълү
    -0.64
    IsContent
    -0.62
    AsUp
    -0.53
    Referencias
    -0.51
    XmlAccessorType
    -0.50
     combineReducers
    -0.49
     nargin
    -0.48
     soeur
    -0.47
     विश्वसनीयता
    -0.45
    POSITIVE LOGITS
     Platon
    0.55
     Tribut
    0.54
     Vessel
    0.54
     Plat
    0.54
    elect
    0.52
     plat
    0.52
     deprecated
    0.51
    Capit
    0.51
     Vesti
    0.50
     Primavera
    0.50
    Activations Density 0.001%

    No Known Activations