© 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. 1-CLT-HP
    7. 9188
    Prev
    Next
    INDEX
    Explanations

    will

    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
     betyder
    -0.50
    dymyr
    -0.50
    JsonProperty
    -0.48
     ujednoznacz
    -0.47
     desple
    -0.47
    Aktualisiert
    -0.47
    temberg
    -0.45
     battled
    -0.44
    AndroidJUnit
    -0.44
    EndProject
    -0.44
    POSITIVE LOGITS
     definitely
    0.75
     surely
    0.73
     تضيفلها
    0.64
     MainAxisSize
    0.62
     certainly
    0.62
    IBOutlet
    0.60
     Surely
    0.60
     not
    0.59
    Surely
    0.59
    ########.
    0.59
    Activations Density 0.013%

    No Known Activations