© 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. 94879
    Prev
    Next
    INDEX
    Explanations

    like

    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
     like
    -1.75
    like
    -1.52
    Like
    -1.36
     Like
    -1.27
     LIKE
    -1.08
     seperti
    -1.04
    LIKE
    -1.00
     zoals
    -0.86
     như
    -0.86
     kuten
    -0.85
    POSITIVE LOGITS
     فريبيس
    0.71
     Roskov
    0.66
    LookAnd
    0.62
     this
    0.61
    DockStyle
    0.60
     Meksiku
    0.59
    AddTagHelper
    0.56
    +#+#
    0.56
     '\\;'
    0.56
     sunscreen
    0.55
    Activations Density 0.078%

    No Known Activations