© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12998
    Prev
    Next
    INDEX
    Explanations

    pal

    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
     Pal
    -1.26
    Pal
    -1.20
     pal
    -1.12
     PAL
    -1.07
    PAL
    -1.05
    pal
    -0.97
     pallet
    -0.81
     Pala
    -0.77
    Palette
    -0.75
     Palatine
    -0.75
    POSITIVE LOGITS
    ukone
    0.58
     />\
    0.52
    PerformLayout
    0.52
    ear
    0.51
    abestanden
    0.47
     Hubble
    0.46
     StringField
    0.46
    Портал
    0.46
    pis
    0.45
    ombie
    0.45
    Activations Density 0.011%

    No Known Activations