© 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. 97542
    Prev
    Next
    INDEX
    Explanations

    dopamine

    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
    du
    -0.51
    ,
    -0.51
     in
    -0.50
    tur
    -0.49
     (
    -0.46
    su
    -0.46
     fre
    -0.45
     du
    -0.45
    OK
    -0.45
     su
    -0.44
    POSITIVE LOGITS
     Efq
    1.23
     iſt
    1.19
     ſche
    1.18
     itſelf
    1.17
     Jefus
    1.13
     myſelf
    1.13
    ſelf
    1.07
     purpoſe
    1.06
     Eſ
    1.05
    ^(@)
    1.02
    Activations Density 0.135%

    No Known Activations