© 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. 0-CLT-HP
    7. 94440
    Prev
    Next
    INDEX
    Explanations

    desirable

    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
     desirable
    -1.27
    valuable
    -1.11
    Personendaten
    -1.02
     desirability
    -0.96
    GraphicsUnit
    -0.95
     Roskov
    -0.94
     undesirable
    -0.91
    viable
    -0.90
    InjectAttribute
    -0.90
    adays
    -0.88
    POSITIVE LOGITS
     career
    0.44
     Let
    0.43
     send
    0.43
     let
    0.42
     Vå
    0.42
     and
    0.42
     latter
    0.41
     execution
    0.40
     way
    0.40
     degree
    0.39
    Activations Density 0.048%

    No Known Activations