Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44948
    Prev
    Next
    INDEX
    Explanations

    contrasting emotions

    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
    ⓧ
    -1.45
    MigrationBuilder
    -1.13
    ^(@)
    -1.08
    Personensuche
    -1.07
    "):
    
    -1.06
    __':
    
    -1.05
     mergeFrom
    -1.05
    BibitemShut
    -1.04
     Мексичка
    -1.03
     snippetHide
    -1.02
    POSITIVE LOGITS
    .
    0.54
    2
    0.54
    4
    0.49
    0
    0.49
    3
    0.48
    5
    0.48
    ,
    0.48
    1
    0.47
    _
    0.47
    6
    0.45
    Activations Density 0.046%

    No Known Activations