© 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. 91913
    Prev
    Next
    INDEX
    Explanations

    professions

    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
    __':
    -0.82
    contentLoaded
    -0.81
    Personendaten
    -0.79
     disambiguazione
    -0.76
    __":
    -0.74
    __':
    -0.73
    __":
    -0.72
    Datuak
    -0.71
    Tikang
    -0.71
    exitRule
    -0.71
    POSITIVE LOGITS
    ’
    0.47
     ervoor
    0.44
    '
    0.43
     daily
    0.40
    ‘
    0.39
    He
    0.39
    至此
    0.37
     entered
    0.37
    jecha
    0.37
     thereto
    0.36
    Activations Density 0.001%

    No Known Activations