© 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. 45149
    Prev
    Next
    INDEX
    Explanations

    lidean

    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
    lidean
    -1.63
    UserScript
    -0.51
     olden
    -0.47
     float
    -0.46
    getRuntime
    -0.46
    lid
    -0.45
     Vu
    -0.44
    lipe
    -0.44
     يونيو
    -0.44
    プレ
    -0.43
    POSITIVE LOGITS
    IndentedString
    0.68
    دانشنامهٔ
    0.64
    oredCriteria
    0.64
     defaultstate
    0.64
    CPtr
    0.64
     purpoſe
    0.61
    CppCodeGen
    0.60
    posedge
    0.60
     Jefus
    0.60
    ApplicationTests
    0.58
    Activations Density 1.129%

    No Known Activations