© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1113
    Prev
    Next
    INDEX
    Explanations

    overview

    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
    descriptions
    -0.53
     Descriptions
    -0.51
     default
    -0.50
     descriptions
    -0.50
    "},
    
    -0.47
    Descriptions
    -0.44
    naam
    -0.44
    '));
    
    -0.44
     Description
    -0.43
    cierto
    -0.41
    POSITIVE LOGITS
    DeleteBehavior
    0.71
    thon
    0.68
     Мексичка
    0.67
    LookAnd
    0.65
    WebElementEntity
    0.65
    Personendaten
    0.63
    hamcrest
    0.63
     pinulongan
    0.63
     beginnetje
    0.63
    ThroughAttribute
    0.62
    Activations Density 0.144%

    No Known Activations