© 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. 39814
    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
    клопе
    -0.71
     beginnetje
    -0.68
    
    -0.68
    CloseOperation
    -0.66
    thâu
    -0.63
     kasarigan
    -0.62
    TemporalType
    -0.61
    Personendaten
    -0.58
     autorytatywna
    -0.58
    jooq
    -0.57
    POSITIVE LOGITS
    ={({
    0.61
     Indu
    0.54
    ERIE
    0.50
    RemoteException
    0.50
    },[])
    0.49
    aux
    0.47
     Prada
    0.47
    itores
    0.47
    őség
    0.46
    דיה
    0.46
    Activations Density 2.215%

    No Known Activations