© 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. 0-CLT-HP
    7. 45144
    Prev
    Next
    INDEX
    Explanations

    could

    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
    GraphicsUnit
    -1.16
     ―――――
    -1.12
     GenerationType
    -1.09
     myſelf
    -1.09
     iſt
    -1.08
     Majefty
    -1.03
     InputDecoration
    -1.02
     ſind
    -1.02
     Anſ
    -1.01
     transfieras
    -1.00
    POSITIVE LOGITS
    ,
    0.88
     can
    0.84
     ‘
    0.84
     (
    0.81
     in
    0.78
     '
    0.77
    /
    0.71
     
    0.71
    :
    0.66
     it
    0.65
    Activations Density 0.045%

    No Known Activations