© 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. 5-CLT-HP
    4. 2097
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     therewith
    -0.56
    ГЛА
    -0.54
     }}"></
    -0.54
    Abit
    -0.53
     therefrom
    -0.53
    
    -0.52
    Datuak
    -0.51
    %</
    -0.50
    \{\\
    -0.49
     MTA
    -0.49
    POSITIVE LOGITS
    NameInMap
    0.57
    /*:
    0.48
     nel
    0.45
     Rechts
    0.44
    1
    0.43
    ביוגרפיה
    0.43
    альное
    0.42
    őben
    0.42
    escens
    0.42
    》。
    0.41
    Activations Density 0.000%

    No Known Activations