© 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. 5037
    Prev
    Next
    INDEX
    Explanations

    birthdates

    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
    .*")]
    -0.84
    WebVitals
    -0.78
     disambiguazione
    -0.73
     nonatomic
    -0.70
    enderror
    -0.68
     GenerationType
    -0.68
    +#+#
    -0.67
    UnusedPrivate
    -0.65
    #+#
    -0.65
     AssemblyCompany
    -0.65
    POSITIVE LOGITS
     Vein
    0.49
     Requis
    0.48
    ursal
    0.48
     Comptroller
    0.44
     stof
    0.44
     getClient
    0.44
    المراجع
    0.43
    needle
    0.43
     thought
    0.42
     providence
    0.42
    Activations Density 0.118%

    No Known Activations