© 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. 4-CLT-HP
    7. 4365
    Prev
    Next
    INDEX
    Explanations

    you

    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
    ่วม
    -0.60
    basicConfig
    -0.56
     referenties
    -0.54
    AutoScaleMode
    -0.54
    wasn
    -0.53
    stands
    -0.53
     Wasn
    -0.52
     IUser
    -0.52
    TextWatcher
    -0.52
    postolic
    -0.52
    POSITIVE LOGITS
     like
    0.79
     call
    0.68
    GraphicsUnit
    0.64
     Like
    0.59
     are
    0.58
    setViewportView
    0.57
    awtextra
    0.54
     Call
    0.53
    SharedCtor
    0.51
    like
    0.50
    Activations Density 0.003%

    No Known Activations